Leverage ML to Spot Anomalies in Real-time Forex Data
3101
Of your peers have already read this article.
6:00 Minutes
The most insightful time you'll spend today!
Let’s say you are a quantitative trader with access to real-time foreign exchange (forex) price data from your favorite market data provider. Perhaps you have a data partner subscription, or you’re using a synthetic data generator to prove value first. You know there must be thousands of other quants out there with your same goal. How will you differentiate your anomaly detector?
What if, instead of training an anomaly detector on raw forex price data, you detected anomalies in an indicator that already provides generally agreed buy and sell signals? Relative Strength Index (RSI) is one such indicator; it is often said that RSI going above 70 is a sell signal, and RSI going below 30 is a buy signal. As this is just a simplified rule, it means there could be times when the signal is inaccurate, such as a currency market correction, making it a prime opportunity for an anomaly detector.
This gives us the following high level components:
Of course, we want each of these components to handle data in real time, and scale elastically as needed. Dataflow pipelines and Pub/Sub are the perfect services for this. All we need to do is write our components on top of the Apache Beam sdk, and they’ll have the benefit of distributed, resilient and scalable compute.
Luckily for us, there are some great existing Google plugins for Apache Beam. Namely, a Dataflow time-series sample library that includes RSI calculations, and a lot of other useful time series metrics; and a connector for using AI Platform or Vertex AI inference within a Dataflow pipeline. Let’s update our diagram to match, where the solid arrows represent Pub/Sub topics.
The Dataflow time-series sample library also provides us with gap-filling capabilities, which means we can rely on having contiguous data once the flow reaches our machine learning (ML) model. This lets us implement quite complex ML models, and means we have one less edge case to worry about.
So far we’ve only talked about the real time data flow, but for visualization and continuous retraining of our ML model, we’re going to want historical data as well. Let’s use BigQuery as our data warehouse, and Dataflow to plumb Pub/Sub into it. As this plumbing job is embarrassingly parallelizable, we wrote our pipeline to be generic across data types and share the same Dataflow job, such that compute resources can be shared. This results in efficiencies of scale both in cost savings and time required to scale-up.
Data Modeling
Let’s discuss data formats a bit further here. An important aspect of running any data engineering project at scale is flexibility, interoperability and ease of debugging. As such, we opted to use flat JSON structures for each of our data types, because they are human readable and ubiquitously understood by tooling. As BigQuery understands them too, it’s easy to jump into the BigQuery console and confirm each component of the project is working as expected.
As you can see, the Dataflow sample library is able to generate many more metrics than RSI. It supports generating two types of metrics across time series windows, metrics which can be calculated on unordered windows, and metrics which require ordered windows, which the library refers to as Type 1 metrics and Type 2 metrics, respectively. Unordered metrics have a many-to-one relationship, which can help reduce the size of your data by reducing the frequency of points through time. Ordered metrics run on the outputs of the unordered metrics, and help to spread information through the time domain without loss in resolution. Be sure to check out the Dataflow sample library documentation for a comprehensive list of metrics supported out of the box.
As our output is going to be interpreted by our human quant, let’s use the unordered metrics to reduce the time resolution of our flow of real time data to one per second, or one hertz. If our output was being passed into an automated trading algorithm, we might choose a higher frequency. The decision for the size of our ordered metrics window is a little more difficult, but broadly determines the amount of time-steps our ML model will have for context, and therefore the window of time for which our anomaly detection will be relevant. We at least need it to be larger than our end-to-end latency, to ensure our quant will have time to act. Let’s set it to five minutes.
Data Visualization
Before we dive into our ML model, let’s work on visualization to give us a more intuitive feel for what’s happening with the metrics, and confirm everything we’ve got so far is working. We use the Grafana helm chart with the BigQuery plugin on a Google Kubernetes Engine (GKE) Autopilot cluster. The visualisation setup is entirely config-driven and provides out-of-the-box scaling, and GKE gives us a place to host some other components later on.
GKE Autopilot has Workload Identity enabled by default, which means we don’t need to worry about passing around secrets for BigQuery access, and can instead just create a GCP service account that has read access to BigQuery and assign it to our deployment through the linked Kubernetes service account.
That’s it! We can now create some panels in a Grafana dashboard and see the gap filling and metrics working in real time.
Building and deploying the Machine Learning Model
Ok, ML time. As we alluded to earlier, we want to continuously retrain our ML model as new data becomes available, to ensure it remains up to date with the current trend of the market. TensorFlow Extended (TFX) is a platform for creating end-to-end machine learning pipelines in production, and eases the process around building a reusable training pipeline. It also has extensions for publishing to AI Platform or Vertex AI, and it can use Dataflow runners, which makes it a good fit for our architecture. The TFX pipeline still needs an orchestrator, so we can host that in a Kubernetes job, and if we wrap it in a scheduled job, then our retraining happens on a schedule too!
TFX requires our data be in the tf.Example format. The Dataflow sample library can output tf.Examples directly, but this tightly couples our two pipelines together. If we want to be able to run multiple ML models in parallel, or train new models on existing historical data, we need our pipelines to only be loosely coupled. Another option is to use the default TFX BigQuery adaptor, but this restricts us to each row in BigQuery mapping to exactly one ML sample, meaning we can’t use recurrent networks.
As neither of the out-of-the-box solutions met our requirements, we decided to write a custom TFX component that did what we needed. Our custom TFX BigQuery adaptor enables us to keep our standard JSON data format in BigQuery and train recurrent networks, and it keeps our pipelines loosely coupled! We need the windowing logic to be the same for both training and inference time, so we built our custom TFX component using standard Beam components, such that the same code can be imported in both pipelines.
def window_elements(pipeline: beam.Pipeline,window_length: int,drop_irregular_windows: bool = True,sort_windows_by: str = "timestamp",):"""Window elements into regular windows of a given size.Assumes elements flow at a fixed rate of 1Hz."""def _sort_windows(window: Iterable[Dict[Text, Any]]) -> List[Dict[Text, Any]]:sorted_window = sorted(window, key=lambda e: e[sort_windows_by])return sorted_windowwindowed_elements = (pipeline| "AddConstantKey" >> beam.Map(lambda item: (0, item))| "WithSlidingWindow">> beam.WindowInto(beam.transforms.window.SlidingWindows(window_length, 1),trigger=beam.transforms.trigger.AfterCount(window_length),accumulation_mode=beam.transforms.trigger.AccumulationMode.DISCARDING,)| "CombineWindow" >> beam.GroupByKey()| "GetValues" >> beam.Values())if drop_irregular_windows:windowed_elements = windowed_elements | "EnforceWindowLengths" >> beam.Filter(lambda w: len(w) == window_length).with_output_types(List[Dict[Text, Any]])if sort_windows_by is not None:windowed_elements = windowed_elements | "Sort" >> beam.Map(_sort_windows).with_output_types(List[Dict[Text, Any]])return windowed_elements
With our custom generator done, we can start designing our anomaly detection model. An autoencoder utilising long-short-term-memory (LSTM) is a good fit for our time-series use case. The autoencoder will try to reconstruct the sample input data, and we can then measure how close it gets. That difference is known as the reconstruction error. If there is a large enough error, we call that sample an anomaly. To learn more about autoencoders, please consider reading chapter 14 from Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville.
Our model uses simple moving average, exponential moving average, standard deviation, and log returns as input and output features. For both the encoder and decoder subnetworks, we have 2 layers of 30 time step LSTMs, with 32 and 16 neurons, respectively.
In our training pipeline, we include z score scaling as a preprocessing transformer – which is usually a good idea when it comes to ML. However, there’s a nuance to using an autoencoder for anomaly detection. We need not only the output of the model, but also the input, in order to calculate the reconstruction error. We’re able to do this by using model serving functions to ensure our model returns both the output and preprocessed input as part of its response. As TFX has out-of-the-box support for pushing trained models to AI Platform, all we need to do is configure the pusher, and our (re)training component is complete.
Detecting Anomalies in real time
Now that we have our model in Google Cloud AI Platform, we need our inference pipeline to call to it in real time. As our data is using standard JSON, we can easily apply our RSI rule of thumb inline, ensuring our model only runs when needed. Using the reconstructed output from AI Platform, we are then able to calculate the reconstruction error. We choose to stream this directly into Pub/Sub to enable us to dynamically apply an anomaly threshold when visualising, but if you had a static threshold you could apply it here too.
with beam.Pipeline(options=pipeline_options) as pipeline:(pipeline| "ReadFromPubSub">> beam.io.ReadFromPubSub(topic=input_metrics,timestamp_attribute=timestamp_key,)| "DeserialiseJSON" >> beam.Map(pubsub_serialiser.to_json)| "FilterSymbol" >> beam.Filter(lambda m: m["symbol"] == symbol)| "FilterRSIThreshold">> beam.Filter(lambda m: m["RELATIVE_STRENGTH_INDICATOR"] > rsi_upper_thresholdor m["RELATIVE_STRENGTH_INDICATOR"] < rsi_lower_threshold)| "WindowElements" >> window_elements(window_length)| "RunAutoencoder">> run_windowed_inference(gcp_project_id,model_name,window_length,{f: "FLOAT" for f in feature_metrics},)| "CalcReconError" >> beam.Map(calc_reconstruction_err)| "ToJSON">> beam.Map(lambda re: {"symbol": symbol, "reconstruction_error": re})| "SerialiseJSON" >> beam.Map(pubsub_serialiser.from_json)| "WriteToPubSub">> beam.io.WriteToPubSub(topic=output_alerts,timestamp_attribute=timestamp_key,))
Summary
Here’s what the wider architecture looks like now:
More importantly though, does it fit for our use case? We can plot the reconstruction error of our anomaly detector against the standard RSI buy/sell signal, and see when our model is telling us that perhaps we shouldn’t blindly trust our rule of thumb. Go get ‘em, quant!
In terms of next steps, there are many things you could do to extend or adapt what we’ve covered. You might want to explore with multi-currency models, where you could detect when the price action of correlated currencies is unexpected, or you could connect all of the Pub/Sub topics to a visualization tool to provide a real-time dashboard.
Give it a try
To finish it all off, and to enable you to clone the repo and set everything up in your own environment, we include a data synthesizer to generate forex data without needing access to a real exchange. As you might have guessed, we host this on our GKE cluster as well. There are a lot of other moving parts – TFX uses a SQL database and all of the application code is packaged into a docker image and deployed along with the infra using Terraform and cloud build. But if you’re interested in those nitty gritty details, head over to the repo and get cloning!
Feel free to reach out to our teams at Google Cloud and Kasna for help in making this pattern work best for your company.
3396
Of your peers have already listened to this podcast
30:54 Minutes
The most insightful time you'll spend today!
AI-as-a-Service is Here. It’s Really Almost Plug-and-Play
Let’s say you are a quantitative trader with access to real-time foreign exchange (forex) price data from your favorite market data provider. Perhaps you have a data partner subscription, or you’re using a synthetic data generator to prove value first. You know there must be thousands of other quants out there with your same goal. How will you differentiate your anomaly detector?
What if, instead of training an anomaly detector on raw forex price data, you detected anomalies in an indicator that already provides generally agreed buy and sell signals? Relative Strength Index (RSI) is one such indicator; it is often said that RSI going above 70 is a sell signal, and RSI going below 30 is a buy signal. As this is just a simplified rule, it means there could be times when the signal is inaccurate, such as a currency market correction, making it a prime opportunity for an anomaly detector.
This gives us the following high level components:
Of course, we want each of these components to handle data in real time, and scale elastically as needed. Dataflow pipelines and Pub/Sub are the perfect services for this. All we need to do is write our components on top of the Apache Beam sdk, and they’ll have the benefit of distributed, resilient and scalable compute.
Luckily for us, there are some great existing Google plugins for Apache Beam. Namely, a Dataflow time-series sample library that includes RSI calculations, and a lot of other useful time series metrics; and a connector for using AI Platform or Vertex AI inference within a Dataflow pipeline. Let’s update our diagram to match, where the solid arrows represent Pub/Sub topics.
The Dataflow time-series sample library also provides us with gap-filling capabilities, which means we can rely on having contiguous data once the flow reaches our machine learning (ML) model. This lets us implement quite complex ML models, and means we have one less edge case to worry about.
So far we’ve only talked about the real time data flow, but for visualization and continuous retraining of our ML model, we’re going to want historical data as well. Let’s use BigQuery as our data warehouse, and Dataflow to plumb Pub/Sub into it. As this plumbing job is embarrassingly parallelizable, we wrote our pipeline to be generic across data types and share the same Dataflow job, such that compute resources can be shared. This results in efficiencies of scale both in cost savings and time required to scale-up.
Data Modeling
Let’s discuss data formats a bit further here. An important aspect of running any data engineering project at scale is flexibility, interoperability and ease of debugging. As such, we opted to use flat JSON structures for each of our data types, because they are human readable and ubiquitously understood by tooling. As BigQuery understands them too, it’s easy to jump into the BigQuery console and confirm each component of the project is working as expected.
As you can see, the Dataflow sample library is able to generate many more metrics than RSI. It supports generating two types of metrics across time series windows, metrics which can be calculated on unordered windows, and metrics which require ordered windows, which the library refers to as Type 1 metrics and Type 2 metrics, respectively. Unordered metrics have a many-to-one relationship, which can help reduce the size of your data by reducing the frequency of points through time. Ordered metrics run on the outputs of the unordered metrics, and help to spread information through the time domain without loss in resolution. Be sure to check out the Dataflow sample library documentation for a comprehensive list of metrics supported out of the box.
As our output is going to be interpreted by our human quant, let’s use the unordered metrics to reduce the time resolution of our flow of real time data to one per second, or one hertz. If our output was being passed into an automated trading algorithm, we might choose a higher frequency. The decision for the size of our ordered metrics window is a little more difficult, but broadly determines the amount of time-steps our ML model will have for context, and therefore the window of time for which our anomaly detection will be relevant. We at least need it to be larger than our end-to-end latency, to ensure our quant will have time to act. Let’s set it to five minutes.
Data Visualization
Before we dive into our ML model, let’s work on visualization to give us a more intuitive feel for what’s happening with the metrics, and confirm everything we’ve got so far is working. We use the Grafana helm chart with the BigQuery plugin on a Google Kubernetes Engine (GKE) Autopilot cluster. The visualisation setup is entirely config-driven and provides out-of-the-box scaling, and GKE gives us a place to host some other components later on.
GKE Autopilot has Workload Identity enabled by default, which means we don’t need to worry about passing around secrets for BigQuery access, and can instead just create a GCP service account that has read access to BigQuery and assign it to our deployment through the linked Kubernetes service account.
That’s it! We can now create some panels in a Grafana dashboard and see the gap filling and metrics working in real time.
Building and deploying the Machine Learning Model
Ok, ML time. As we alluded to earlier, we want to continuously retrain our ML model as new data becomes available, to ensure it remains up to date with the current trend of the market. TensorFlow Extended (TFX) is a platform for creating end-to-end machine learning pipelines in production, and eases the process around building a reusable training pipeline. It also has extensions for publishing to AI Platform or Vertex AI, and it can use Dataflow runners, which makes it a good fit for our architecture. The TFX pipeline still needs an orchestrator, so we can host that in a Kubernetes job, and if we wrap it in a scheduled job, then our retraining happens on a schedule too!
TFX requires our data be in the tf.Example format. The Dataflow sample library can output tf.Examples directly, but this tightly couples our two pipelines together. If we want to be able to run multiple ML models in parallel, or train new models on existing historical data, we need our pipelines to only be loosely coupled. Another option is to use the default TFX BigQuery adaptor, but this restricts us to each row in BigQuery mapping to exactly one ML sample, meaning we can’t use recurrent networks.
As neither of the out-of-the-box solutions met our requirements, we decided to write a custom TFX component that did what we needed. Our custom TFX BigQuery adaptor enables us to keep our standard JSON data format in BigQuery and train recurrent networks, and it keeps our pipelines loosely coupled! We need the windowing logic to be the same for both training and inference time, so we built our custom TFX component using standard Beam components, such that the same code can be imported in both pipelines.
def window_elements(pipeline: beam.Pipeline,window_length: int,drop_irregular_windows: bool = True,sort_windows_by: str = "timestamp",):"""Window elements into regular windows of a given size.Assumes elements flow at a fixed rate of 1Hz."""def _sort_windows(window: Iterable[Dict[Text, Any]]) -> List[Dict[Text, Any]]:sorted_window = sorted(window, key=lambda e: e[sort_windows_by])return sorted_windowwindowed_elements = (pipeline| "AddConstantKey" >> beam.Map(lambda item: (0, item))| "WithSlidingWindow">> beam.WindowInto(beam.transforms.window.SlidingWindows(window_length, 1),trigger=beam.transforms.trigger.AfterCount(window_length),accumulation_mode=beam.transforms.trigger.AccumulationMode.DISCARDING,)| "CombineWindow" >> beam.GroupByKey()| "GetValues" >> beam.Values())if drop_irregular_windows:windowed_elements = windowed_elements | "EnforceWindowLengths" >> beam.Filter(lambda w: len(w) == window_length).with_output_types(List[Dict[Text, Any]])if sort_windows_by is not None:windowed_elements = windowed_elements | "Sort" >> beam.Map(_sort_windows).with_output_types(List[Dict[Text, Any]])return windowed_elements
With our custom generator done, we can start designing our anomaly detection model. An autoencoder utilising long-short-term-memory (LSTM) is a good fit for our time-series use case. The autoencoder will try to reconstruct the sample input data, and we can then measure how close it gets. That difference is known as the reconstruction error. If there is a large enough error, we call that sample an anomaly. To learn more about autoencoders, please consider reading chapter 14 from Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville.
Our model uses simple moving average, exponential moving average, standard deviation, and log returns as input and output features. For both the encoder and decoder subnetworks, we have 2 layers of 30 time step LSTMs, with 32 and 16 neurons, respectively.
In our training pipeline, we include z score scaling as a preprocessing transformer – which is usually a good idea when it comes to ML. However, there’s a nuance to using an autoencoder for anomaly detection. We need not only the output of the model, but also the input, in order to calculate the reconstruction error. We’re able to do this by using model serving functions to ensure our model returns both the output and preprocessed input as part of its response. As TFX has out-of-the-box support for pushing trained models to AI Platform, all we need to do is configure the pusher, and our (re)training component is complete.
Detecting Anomalies in real time
Now that we have our model in Google Cloud AI Platform, we need our inference pipeline to call to it in real time. As our data is using standard JSON, we can easily apply our RSI rule of thumb inline, ensuring our model only runs when needed. Using the reconstructed output from AI Platform, we are then able to calculate the reconstruction error. We choose to stream this directly into Pub/Sub to enable us to dynamically apply an anomaly threshold when visualising, but if you had a static threshold you could apply it here too.
with beam.Pipeline(options=pipeline_options) as pipeline:(pipeline| "ReadFromPubSub">> beam.io.ReadFromPubSub(topic=input_metrics,timestamp_attribute=timestamp_key,)| "DeserialiseJSON" >> beam.Map(pubsub_serialiser.to_json)| "FilterSymbol" >> beam.Filter(lambda m: m["symbol"] == symbol)| "FilterRSIThreshold">> beam.Filter(lambda m: m["RELATIVE_STRENGTH_INDICATOR"] > rsi_upper_thresholdor m["RELATIVE_STRENGTH_INDICATOR"] < rsi_lower_threshold)| "WindowElements" >> window_elements(window_length)| "RunAutoencoder">> run_windowed_inference(gcp_project_id,model_name,window_length,{f: "FLOAT" for f in feature_metrics},)| "CalcReconError" >> beam.Map(calc_reconstruction_err)| "ToJSON">> beam.Map(lambda re: {"symbol": symbol, "reconstruction_error": re})| "SerialiseJSON" >> beam.Map(pubsub_serialiser.from_json)| "WriteToPubSub">> beam.io.WriteToPubSub(topic=output_alerts,timestamp_attribute=timestamp_key,))
Summary
Here’s what the wider architecture looks like now:
More importantly though, does it fit for our use case? We can plot the reconstruction error of our anomaly detector against the standard RSI buy/sell signal, and see when our model is telling us that perhaps we shouldn’t blindly trust our rule of thumb. Go get ‘em, quant!
In terms of next steps, there are many things you could do to extend or adapt what we’ve covered. You might want to explore with multi-currency models, where you could detect when the price action of correlated currencies is unexpected, or you could connect all of the Pub/Sub topics to a visualization tool to provide a real-time dashboard.
Give it a try
To finish it all off, and to enable you to clone the repo and set everything up in your own environment, we include a data synthesizer to generate forex data without needing access to a real exchange. As you might have guessed, we host this on our GKE cluster as well. There are a lot of other moving parts – TFX uses a SQL database and all of the application code is packaged into a docker image and deployed along with the infra using Terraform and cloud build. But if you’re interested in those nitty gritty details, head over to the repo and get cloning!
Feel free to reach out to our teams at Google Cloud and Kasna for help in making this pattern work best for your company.
Home Depot’s Interconnected Retail Experience by Virtue of Google Cloud Migration for SAP Applications
8260
Of your peers have already read this article.
1:30 Minutes
The most insightful time you'll spend today!
With nearly 2,300 stores, The Home Depot is the world’s largest home-improvement chain — a brand that professional contractors and DIYers alike have come to depend on. The home improvement industry continues to experience unprecedented demand and dramatic increases in online ordering accompanied by expanding consumer expectations for things like curbside pickup and same day delivery. The Home Depot’s decision to migrate to cloud-based infrastructure, including the migration of the company’s SAP applications on Google Cloud which began in 2017, has set it up for success in an increasingly digital world, and helped the company adapt to changing market conditions quickly.
Interconnected retail at scale
Building on a strong customer-first philosophy, The Home Depot aims to create what it calls interconnected retail—allowing customers to shop however, whenever, and wherever they want. “So many companies are focused on omni-channel retail,” explains Sam Moses, Vice President of Corporate Systems. “At The Home Depot, we wanted to take it to the next level. Interconnected retail puts the customer at the center of everything and enables them to shop in store, online, or both. Customers can begin a transaction online and continue in-store, or vice-versa.”
To support this strategy, the company’s SAP environment needed to be more agile. Running everything on-premises, from central finance to POS systems, meant that The Home Depot’s IT teams experienced redundancy and repetitive, manual processes. Their data warehouse needed an upgrade to process and analyze growing and increasingly diverse data sets. The Home Depot chose to migrate its SAP environment to Google Cloud to support both the velocity and scale needed for the business as well as critical analytics capabilities needed for its bold digital initiatives. “We chose Google Cloud to support our SAP implementation. Our decision had a lot to do with the relationship between Google Cloud and SAP and also for the applications and services that are offered by Google Cloud, like BigQuery, which are helping to enable data and analytics within our organization,” Moses explains.
After migrating its SAP applications—including S/4HANA, its customer activity repository (CAR), general ledger, e-commerce system, enterprise data warehouse and more to Google Cloud, the company now has the speed, scale and flexibility to tackle enormous spikes in the business, all while staying fully available for their customers. Additionally, The Home Depot was able to transform its financial systems and make them more agile to deliver critical information across multiple business functions in real time.
Maximizing data insights to support customer experiences
By migrating to Google Cloud, The Home Depot is leveraging Google Cloud analytics to build the industry’s most efficient supply chain including more robust demand forecasting, supplier lead times, estimated delivery times and more, all while maintaining better security than before. “We experienced unprecedented change in our customers’ behavior and their buying patterns, which puts a lot of pressure on our supply chain,” explains Moses. “So having the ability to leverage data and analytics gives us insights to know exactly what it is that our customers need.”
The company’s analysts now use BigQuery ML for machine learning directly against the company’s BigQuery data and use AutoML to determine the best model for predictions. The Home Depot’s engineers have also adapted BigQuery to monitor, analyze, and act on application performance data across all its stores and warehouses in real time—capabilities that were not as seamless in the on-premises environment.
With hundreds of projects on Google Cloud, The Home Depot’s cloud journey is well on track, but the company is always looking to the future. “As our customers’ needs have continued to evolve, and as technology has continued to evolve, our relationship with Google will continue to advance — to be able to innovate together, to be able to find new solutions together, to better serve our customers.”
Learn more about how The Home Depot is renovating its retail operation with SAP on Google Cloud.
How Domino’s Increased Monthly Revenue By 6% with Google Marketing Platform
DOWNLOAD CASE STUDY5765
Of your peers have already downloaded this article
1:30 Minutes
The most insightful time you'll spend today!
Pizza purveyor Domino’s is dominating delivery sales around the world. Today, Domino’s is the most popular pizza delivery chain operating in the U.K., the Republic of Ireland, Germany, and Switzerland — and sales just keep growing.
In these regions in 2014, Domino’s sold 76 million pizzas and generated £766.6 million (1.02 billion USD) in revenue — a 14.6% increase from the previous year.
In the U.K. and Ireland, online sales are increasing 30% year over year and currently account for almost 70% of all sales. Notably, 44% of those online sales are now made via mobile devices.
Multi-Device Purchasing Means Fresh Opportunities
Domino’s is a consistent digital innovator. Much of the company’s success stems from early investments in ecommerce and mobile commerce platforms that help people easily purchase pizzas from different devices.
Domino’s sold its first pizza online in 1999. It then launched an iPhone app in 2010, quickly followed by apps for Android and iPad in 2011, and a Windows app in 2012. By late 2014, Domino’s customers could even order pizzas from Xboxes.
The Domino’s marketing team had assembled a variety of tools to measure marketing performance, keeping pace with the company’s rapid innovations. Unfortunately, measuring siloed analytics and channel-focused tools restricted the team’s ability to fully understand all of the different paths to purchase.
Find out how they worked around this challenge with Google Marketing Platform. Download the case study!
US County, the Size of Mangalore, Uses AI to Offer Voice-Enabled Virtual Agent
3060
Of your peers have already read this article.
5:30 Minutes
The most insightful time you'll spend today!
From the historic Gold Country to the rugged heights of the Sierra Nevada, Placer County encompasses more than 1,500 square miles—and provides services to nearly 400,000 residents. Across the county, residents access resources in person, over the phone, and through the county website. In 2018, the county piloted a suite of eServices through its Community Development Resource Agency (CDRA) with the goal of helping its geographically dispersed population more easily apply for permits, make appointments, and get immediate answers to specific questions.
Now, with the help of Google Cloud Dialogflow and Speech-to-Text API, the county has created a virtual agent that enables anyone, anywhere, to simply start a conversation by saying “Ask Placer County” into a variety of voice assistant hardware. This virtual agent builds on the success of eServices and helps the public access information through their smartphones or smart home devices, which is especially helpful for individuals without immediate access to a computer—such as the traveling public or a contractor working on-site, for example.
The pilot program has been an opportunity to explore new technology and create another communication channel to our citizens. “Our ambitious and long-term goal is that ‘Ask Placer County’ will be like having a personal assistant to everything related to Placer County. While the virtual agent is currently limited to a few departments, we plan to expand it countywide,” says Ben Palacio, senior IT analyst for Placer County.
“Our ambitious and long-term goal is that ‘Ask Placer County’ will be like having a personal assistant to everything related to Placer County. While the virtual agent is currently limited to a few departments, we plan to expand it countywide.”
—Ben Palacio, Senior IT Analyst, Placer County
New eServices get a boost from AI virtual agent
The CDRA, one of many departments and agencies within Placer County, deployed interactive eServices for residents. As part of this initiative, the CDRA made a special request to the information technology (IT) department: Build an AI-based virtual agent that would spotlight the eServices on the website and make them easily available through a conversational interface.
“Having a specific technology requirement voiced by an agency was visionary and very welcome. It meant they were engaged and excited about the possibilities that these new technologies had to offer,” says Mike Spak, IT Manager for Placer County.
Today, the CDRA’s eServices help residents answer important questions, such as: “Is my land zoned for adding a garage?” “What historical engineering work has been done on my property?” And, “How can I make an appointment at a permitting office?”
“Having a specific technology requirement voiced by an agency was visionary and very welcome. It meant they were engaged and excited about the possibilities that these new technologies had to offer.”
—Mike Spak, IT Manager, Placer County
Google Cloud fit easily into Placer County’s multivendor environment
With the help of consultants from Dito, a Google Cloud Premier Partner, Placer County chose Google Cloud to help with “Ask Placer County.”
Placer County runs a multivendor IT environment. “Especially with the cloud, the easier it is to integrate a vendor’s capabilities with others, the better for everybody,” says Palacio. “Google Cloud was able to integrate with other vendors’ capabilities for this project.”
For example, Placer County uses the Google Cloud operations suite (formerly Stackdriver) to monitor, troubleshoot, and improve its cloud infrastructure and application performance. And it uses Dialogflow, which powers the natural language processing (NLP) interface of the “Ask Placer County” virtual agent. Both integrate easily with tools from other vendors.
“Especially with the cloud, the easier it is to integrate a vendor’s capabilities with others, the better for everybody. Google Cloud was able to integrate with other vendors’ capabilities for this project.”
—Ben Palacio, Senior IT Analyst, Placer County
Real-time conversations powered by “Ask Placer County”
Dito got “Ask Placer County” up and running using App Engine and Datastore. Today, the “Ask Placer County” virtual agent provides information ranging from how to adopt a pet to short-term-rental compliance.
Users can say “Ask Placer County” into their smartphones or their computer microphones and access targeted information from the pilot departments. IT staff reviews the asked questions and are constantly updating the virtual agent to provide more accurate and responsive information.
“You could be in your backyard with a contractor trying to get a project started, and if the contractor has a question about permitting or zoning, they can use their smartphone to get an answer right then and there, rather than having to interrupt the meeting, get back in their car, and drive to a county office,” says Palacio.
The county hopes “Ask Placer County” will improve the efficiency of in-person interactions between the public and county employees as well. Because the public can access common questions and information online or through the virtual agent, employees’ interactions with the public can be more focused and productive.
“We are providing more effective and efficient service to our customers through 24/7 access to information and by reducing the proportion of staff’s time in responding to emails and voicemails to answer our customer questions,” says Shawna Purvines, Principal Planner for Placer County.
According to Placer County, the virtual agent currently answers a monthly average of around 200 questions for the CDRA, and the county continues to develop more and more complete answers across participating departments.
“We are providing more effective and efficient service to our customers through 24/7 access to information and by reducing the proportion of staff’s time in responding to emails and voicemails to answer our customer questions.”
—Shawna Purvines, Principal Planner, Placer County
Constantly evolving based on users’ needs
To best serve the needs of the CDRA, and potentially other departments over time, “Ask Placer County” continues to evolve. The county can add and retire questions based on the needs of constituents. This technology can be tailored to address current needs, such as responding to COVID-19. “Our hope is that, in quickly evolving situations, the virtual agent can be a resource for the public to access real-time information about public services,” says Palacio.
As a component of the eServices group, “Ask Placer County” has kept construction and development in Placer County operational during the COVID-19 pandemic, and it continues to provide opportunities for the public to access county resources without coming in to the counters, reducing the need for in-person visits. In fact, according to Placer County data, permit applications have increased by 17%.
Placer County also performs analytics using the Google Cloud operations suite to gain insights into the most popular questions and, just as importantly, the questions that are not being answered. “We get insight into what we’re missing—for those times when the virtual agent can’t find a response in our database,” says Palacio. Placer County uses these insights to improve answers and ultimately improve the efficacy of the virtual agent over time.
“This continual, real-time learning is the exciting part of the application that lets us help constituents in entirely new ways. It’s really cool,” says Palacio.
County IT workers actively analyze CDRA webpages to determine which are the most visited and to craft questions and answers to add to “Ask Placer County.” According to Placer County, the number of questions the virtual agent can answer is now more than 600. But the CDRA pages are just a small subset of the 5,000 pages that make up the Placer County website. A future goal is to provide a backstop for customer questions that can’t be answered, transferring those customers to county staff for resolution.
“Looking ahead, this technology has the ability to provide answers to thousands and thousands of questions,” says Palacio.
“This continual, real-time learning is the exciting part of the application that lets us help constituents in entirely new ways. It’s really cool.”
—Ben Palacio, Senior IT Analyst, Placer County
Scaling “Ask Placer County” countywide
The limited rollout of the virtual agent technology allowed IT to monitor its effectiveness and make initial adjustments. As the virtual agent evolves, the Placer County chief information officer sees opportunities for it to engage the public countywide.
The “Ask Placer County” virtual agent can truly be a concierge, helping the public navigate county resources. It can help citizens become more engaged with their elected officials, it can provide information, and it can more efficiently connect the public with the services they seek.
Some of the future possibilities include providing current information on board meetings and individual elected officials, checking on permit status and burn days, and getting the latest county news. “There are so many ways we can use this solution to tackle issues within the county that we’re going to have to somehow prioritize them,” says Palacio.
Analytics Hub for Secure Data Sharing and Analytics Unlocks True Data Value and Insights
6738
Of your peers have already read this article.
2:30 Minutes
The most insightful time you'll spend today!
Customers tell us that sharing and exchanging data with other organizations is a critical element of their analytics strategy, but it’s hamstrung by unreliable data and processes, and only getting harder with security threats and privacy regulations on the rise.
Furthermore, traditional data sharing techniques use batch data pipelines that are expensive to run, create late arriving data, and can break with any changes to the source data. They also create multiple copies of data, which brings unnecessary costs and can bypass data governance processes. These techniques do not offer features for data monetization, such as managing subscriptions and entitlements. Altogether, these challenges mean that organizations are unable to realize the full potential of transforming their business with shared data.
To address these limitations, we are introducing Analytics Hub, a new fully managed service, available in Q3, in preview, that helps you unlock the value of data sharing, leading to new insights and increased business value. With Analytics Hub you get:
- A rich data ecosystem by publishing and subscribing to analytics-ready datasets.
- Control and monitoring over how your data is being used, because data is shared in one place.
- A self-service way to access valuable and trusted data assets, including data provided by Google. For example, a unique dataset from Google Search Trends will be available, that you can query and combine with your own data.
- An easy way to monetize your data assets without the overhead of building and managing the infrastructure.
Built on a decade of cross-organizational sharing
While Analytics Hub is a new service, it builds on BigQuery, Google’s petabyte-scale, serverless cloud data warehouse. BigQuery’s unique architecture provides separation between compute and storage, enabling data publishers to share data with as many subscribers as you want without having to make multiple copies of your data. With BigQuery, there are no servers to deploy or manage, which means that data consumers get immediate value from shared data. Data can be provided and consumed in real-time using the streaming capabilities of BigQuery and you can leverage the built in machine learning, geospatial, and natural language capabilities of BigQuery or take advantage of the native business intelligence support with tools like Looker, Google Sheets, and Data Studio.
BigQuery has had cross-organizational, in-place data sharing capabilities since it was introduced in 2010. We took a look at usage metrics in BigQuery and found that over a 7 day period in April, we had over 3,000 different organizations sharing over 200 petabytes of data. These numbers don’t include data sharing between departments within the same organization.
As you can see, data sharing in BigQuery is already popular. But we want to make it easier and even more scalable.
Raising the bar on data sharing
To make data sharing easier and more scalable in BigQuery, Analytics Hub introduces the concepts of shared datasets and exchanges. As a data publisher, you create shared datasets that contain the views of data that you want to deliver to your subscribers. Next, you create exchanges, which are used to organize and secure shared datasets. By default, exchanges are completely private, which means that only the users and groups that you give access to can view or subscribe to the data. You can also create internal exchanges or leverage public exchanges provided by Google. Finally, you publish shared datasets into an exchange to make them available to subscribers.
Data subscribers search through the datasets that are available across all exchanges for which they have access and subscribe to relevant datasets. This creates a linked dataset in their project that they can query and join with their own data. Subscribers pay for the queries that they run against the data while the publisher pays for the storage of the data. Data providers can add new data, new tables, or new columns to the shared dataset and these will be immediately available to subscribers. In addition, the publisher can track subscribers, disable subscriptions, and see aggregated usage information for the shared data.
Analytics Hub makes it easy for you to publish, discover, and subscribe to valuable datasets that you can combine with your own data to derive unique insights. Here are some types of data that will be available through Analytics Hub:
- Public datasets: Easy access to the existing repository of over 200 public datasets, including data about weather and climate, cryptocurrency, healthcare and life sciences, and transportation.
- Google datasets: Unique, freely-available datasets from Google. One example of this is the COVID-19 community mobility dataset. Another example is the forthcoming Google Trends dataset, which will provide the top 25 search terms and top 25 rising search terms over a 5 year window in 210 distinct locations in the US. Trends data can be used by everyone in the organization to gain insights into what customers care about.
- Commercial (paid for) datasets: We are working with leading commercial data providers to bring their data products to Analytics Hub. If you are interested in delivering your data via Analytics Hub, we’re also introducing Data Gravity, an initiative that provides storage benefits and new distribution paths for data published through Analytics Hub.
- Internal datasets: We know that data sharing can be challenging in larger organizations. Analytics Hub can be used for internal data, for example, to share standardized customer demographics with your sales engineering and data science teams.
Customers and partners using Analytics Hub
“Google Search Trends data has always been an important tool for our WPP agency data teams. At WPP we believe that data variety is a superpower which is why we are excited to use the new Trends dataset availability within BigQuery, plus the launch of Analytics Hub. The best creativity in the world is informed by data insights, and influenced by what people search for, so the operational efficiencies we’ll gain via the Analytics Hub and the insights we can drive with Trends data are just phenomenal.”
—Di Mayze Global Head of Data and AI, WPP
“Equifax Ignite is our shared data analytics environment within our Equifax data fabric. We are excited to partner with Google to leverage Analytics Hub and BigQuery to deliver data to over 400 statisticians and data modelers as well as securely sharing data with our partner financial institutions.”
—Kumar Menon, SVP Data Fabric and Decision Science, Equifax
“The flow of data and insights between our teams at Deloitte and our clients is paramount for building truly transformational data cultures. With its purpose-built architecture for secure data exchanges and sharing analytics resources, Google Cloud’s Analytics Hub can help provide significant operational efficiencies for how Deloitte teams support our clients’ data-driven initiatives within their industry ecosystems. It will also help minimize the worries about scale, privacy and security, or the administrative burden associated with each.”
—Navin Warerkar, Managing Director, Deloitte Consulting LLP, and US Google Cloud Data & Analytics GTM Lead
“Crux Informatics is proud to partner with Google to support the launch of Analytics Hub, removing friction for those who need access to analytics-ready data. With thousands of datasets from over 140 sources, Crux Informatics will accelerate access to data on Analytics Hub and together provide a more efficient and cost effective solution to deliver datasets in Google Cloud’s ecosystem.”
—Will Freiberg, CEO, Crux Informatics
Next steps for Analytics Hub
This is just the beginning for Analytics Hub. As we get to preview and general availability, we will be adding additional capabilities, including workflows for publishing and subscribing, publishing analytics assets (Looker Blocks, Data Studio reports, Connected Google Sheets) along with the shared data, the ability for data publishers to specify query restrictions on the usage of their data, and making it easy for data publishers to create sandbox environments for subscribers to work with their data, even if they are not yet on Google Cloud. We will provide features in Analytics Hub for monetization of data, including managing subscriptions, data entitlements, and billing.
Please sign up for the preview, which is scheduled to be available in the third quarter of 2021. In the meantime, you can learn more about BigQuery and how to leverage its built-in data sharing capabilities. Please go to g.co/cloud/analytics-hub to register your interest in Analytics Hub.
More Relevant Stories for Your Company
Video: How AI is Helping Biologists Protect Wildlife
According to the World Wildlife Fund, vertebrate populations have shrunk an average of 60 percent since the 1970s. And a recent UN global assessment found that we’re at risk of losing one million species to extinction, many of which may become extinct within the next decade. To better protect wildlife, seven organizations, led
Google Cloud expands availability of enterprise-ready generative AI
Generative AI continues to develop at a blistering pace, making it more important than ever that organizations have access to enterprise-ready capabilities to help them leverage this disruptive technology. Harnessing the power of decades of Google’s research, innovation, and investment in AI, Google Cloud continues to make generative AI available
Measuring and Improving Speech-to-Text Accuracy
Google Cloud’s Speech-to-Text API has a large number of uses including making customer service teams more effective and increasing their ability to improve customer experience. Google Cloud’s Speech-to-Text API provides incredible accuracy out of the box. What many might not know is that it also has new tools for enhancing
Survey: What Everyone Else In Your Industry is Doing with AI
Across industries and use cases, organizations that have implemented ML report demonstrable return on investment and substantial business benefits ranging from better, faster data analysis to improved efficiency and cost savings. The vast majority of early adopters — nearly 90 percent, according to one study — believe that ML provides
