For a business to succeed in the long term, it needs to learn not just to adapt to inevitable change, but to harness it. South Africa-based PPS has been an insurance company since 1941 and today is the biggest mutual insurance provider in the country.

As a mutual company, PPS is owned by more than 200,000 members, making them shareholders. In recent years, PPS and other companies like it have been affected by a number of external factors.

“For one thing, technology platforms have brought in a new gig economy that has all kinds of implications for insurance,” says Avsharn Bachoo, CTO at PPS. “What we’ve been seeing is basically a disruption of the South African insurance industry. We chose to see that as an opportunity.”

“Our servers were at the end of their life cycle and we had to decide whether to refresh them or switch completely. To embrace the world of AI and machine learning effectively, we knew we needed a cloud-based infrastructure. We’ve found the answer in Google Cloud Platform.”

—Avsharn Bachoo, CTO, PPS

In early 2018, faced with an uncertain economic environment that was squeezing growth and profitability, PPS decided to transform itself from a traditional broker-based business into a digital insurance provider. A key pillar of this new strategy was to overhaul the company’s technology infrastructure. To turn the strategy into reality, Avsharn and his team chose Google Cloud Platform (GCP).

“Our servers were at the end of their life cycle and we had to decide whether to refresh them or switch completely,” says Avsharn. “To embrace the world of AI and machine learning (ML) effectively, we knew we needed a cloud-based infrastructure. We’ve found the answer in Google Cloud Platform.”

Power, speed, flexibility with Google Cloud Platform

Previously, PPS maintained an on-premises IT infrastructure, which worked for its traditional business but was unsuited for its new way of working. In early 2018, the company started working on new products for its members but this required large amounts of compute power that proved prohibitively expensive with on-premises servers. Even existing products were starting to require more than the infrastructure could deliver. Aging equipment meant that it’s testing and quality assurance environments bore little resemblance to the actual production environment.

“We had no pre-production environments at all,” says Avsharn, resulting in more work for developers after products had been released. Meanwhile, the capital required to buy and configure more servers for new projects meant fewer resources available for innovation, and left the company less able to react to changes in the market. PPS knew it had to find a cloud-based alternative.

Shortly after devising a new digital strategy, PPS engineers attended a training session on cloud infrastructure given by leading South African Google Cloud Partner Siatik. Impressed with the presentation, PPS engaged Siatik to help run a proof of concept for a cloud-based infrastructure, running on GCP. With on-site engineers and constant communication, Siatik formed a very close working relationship with PPS. “The team at Siatik was exemplary,” recalls Avsharn. “They were well-organized, with cutting-edge technical acumen and very creative solutions to our problems. They were real game-changers.”

“We wanted the platform to retrain its models in response to new data and improve its recommendations with more information. Normally this would be a manual process but Google Cloud ML Engine lets the models do this automatically.”

—Kimoon Kim, Lead Solution Architect and Data Engineer, Siatik

The proof of concept was successful, with GCP outperforming the existing infrastructure in terms of how it handled compute demands, databases, and storage.

“It’s the speed of GCP that really impresses us,” says Avsharn. PPS saw that GCP wasn’t just an opportunity to migrate its existing infrastructure to the cloud. With Siatik’s help, it redesigned its monolithic core architecture to one based around microservices using Google Kubernetes Engine (GKE). For data processing and storage, Cloud Dataflow and Cloud Datastore proved invaluable, while Stackdriver helped the IT team stay on top of logging and monitoring the system.

“Google Cloud makes migrations very easy,” says Brett St. Clair, CEO at Siatik. “It takes care of all the hard work with configurations and replications, so when we switch the machines on, everything is ready and working.”

The ease with which PPS migrated to GCP means that it can now tackle strategic goals much more quickly than before. The most ambitious of these is an AI-powered product recommendation platform. Information is collected from customers who opt in at a defined point in their journey, this database is queried using BigQuery, and the information is fed into the platform. The AI model then calculates the most appropriate products for each member, according to their personal history.

“Most of the product recommendation engines out there are based on clustering, where you’re offered products based on your peer groups,” explains Avsharn. “For the first time, we can make recommendations to members based on their individual preferences and historical behavior. That’s really powerful for us.”

Siatik helped PPS use TensorFlow and Cloud Machine Learning Engine to build the AI platform. For the engineers, these easy-to-use tools helped speed up the process considerably, allowing them to host the models locally without any fuss. Previously, it took one to three months to manually build the model and match an offer to a customer. With the AI platform, a match takes just a few minutes. Cloud ML Engine, in particular, helped the platform adapt to new information on the fly and easily make adjustments to its hyperparameters, that is, preset variables which define the model-training process.

“We wanted the platform to retrain its models in response to new data and improve its recommendations with more information,” says Kimoon Kim, Lead Solution Architect and Data Engineer at Siatik. “Normally this would be a manual process but Google Cloud ML Engine lets the models do this automatically.”

“Google Cloud helped us cancel out a lot of the noise around machine learning and AI. We don’t have to build new complicated algorithms or hire huge teams of data scientists to benefit. We just bring our data and use the right tools to focus on what’s really important.”

—Avsharn Bachoo, CTO, PPS

Harnessing artificial intelligence for real-world results

PPS deployed its new AI recommendation platform in December, 2018. Just a couple of months later, its impact was clear. “In around eight weeks, we saw a 5 percent growth in sales,” says Avsharn. “It’s been a direct result of building our recommendation platform with Google Cloud. We can offer the right products to the right members.”

For developers and engineers at PPS, working with Google Cloud gives them access to high performance technology and automation options with GKE. As a result, the infrastructure runs 70 percent faster than before with fewer cores and less memory. Developers can also work in mature testing environments, and for the first time, are able to build pre-production environments, leading to better quality products. More strategically, moving to a serverless, cloud-based infrastructure has helped PPS take control of its budget, moving away from intermittent, large capital spends to more manageable, project-to-project flows of operational expenditure. The company expects to see savings of around 50 percent, or $695,000.

“We have a lot more flexibility with our resources thanks to Google Cloud,” says Avsharn. “When we have a new idea, we don’t have to outlay new capital such as servers before we can even start working on it. We just spin up instances when we want and spin them back down when we’re done.”

With the AI platform deployed and working well, PPS is already looking at ways to improve it, including real-time updates and further automation. Soon, the company will integrate the platform with more sales campaigns for more effective targeting to boost sales even further. Meanwhile, it’s also experimenting with machine learning to spot patterns in data at scale for fraud analytics and risk assessment.

For PPS, working with Google Cloud has helped it transform quickly and effectively from disrupted to disruptor. The company is now looking to gain the same transformative effects by implementing G Suite for increased productivity and collaboration.

“Google Cloud helped us cancel out a lot of the noise around machine learning and AI,” says Avsharn. “We don’t have to build new complicated algorithms or hire huge teams of data scientists to benefit. We just bring our data and use the right tools to focus on what’s really important.”

Explainable AI (XAI) helps you understand and interpret how your machine learning models make decisions. We’re excited to announce that BigQuery Explainable AI is now generally available (GA). BigQuery is the data warehouse that supports explainable AI in a most comprehensive way w.r.t both XAI methodology and model types. It does this at BigQuery scale, enabling millions of explanations within seconds with a single SQL query.

Why is Explainable AI so important? To demystify the inner workings of machine learning models, Explainable AI is quickly becoming an essential and growing need for businesses as they continue to invest in AI and ML. With 76% of enterprises now prioritizing artificial intelligence (AI) and machine learning (ML) over other initiatives in 2021 IT budgets, the majority of CEOs (82%) believe that AI-based decisions must be explainable to be trusted according to a PwC survey.

While the focus of this blogpost is on BigQuery Explainable AI, Google Cloud provides a variety of tools and frameworks to help you interpret models outside of BigQuery, such as with Vertex Explainable AI, which includes AutoML Tables, AutoML Vision, and custom-trained models.

So how does Explainable AI in BigQuery work exactly? And how might you use it in practice? 

Two types of Explainable AI: global and local explainability

When it comes to Explainable AI, the first thing to note is that there are two main types of explainability as they relate to the features used to train the ML model: global explainability and local explainability.

Imagine that you have a ML model that predicts housing price (as a dollar amount), based on three features: (1) number of bedrooms, (2) distance to the nearest city center, and (3) construction date.

Global explainability (a.k.a. global feature importance) describes the features’ overall influence on the model and helps you understand if a feature had a greater influence than other features over the model’s predictions. For example, global explainability can reveal that the number of bedrooms and distance to city center typically has a much stronger influence than the construction date on predicting housing prices. Global explainability is especially useful if you have hundreds or thousands of features and you want to determine which features are the most important contributors to your model. You may also consider using global explainability as a way to identify and prune less important features to improve the generalizability of their models.

Local explainability (a.k.a. feature attributions) describes the breakdown of how each feature contributes towards a specific prediction. For example, if the model predicts that house ID#1001 has a predicted price of $230,000, local explainability would describe a baseline amount (e.g. $50,000) and how each of the features contributes on top of the baseline towards the predicted price. For example, the model may say that on top of the baseline of $50,000, having 3 bedrooms contributed an additional $50,000, close proximity to the city center added $100,000, and construction date of 2010 added $30,000, for a total predicted price of $230,000. In essence, understanding the exact contribution of each feature used by the model to make each prediction is the main purpose of local explainability.

What ML models does BigQuery Explainable AI apply to?

BigQuery Explainable AI applies to a variety of models, including supervised learning models for IID data and time series models. The documentation for BigQuery Explainable AI provides an overview of the different ways of applying explainability per model. Note that each explainability method has its own way of calculation (e.g. Shapley values), which are covered more in-depth in the documentation.

Examples with BigQuery Explainable AI

In this next section, we will show three examples of how to use BigQuery Explainable AI in different ML applications: 

• regression 
• classification
• time-series forecasting

Regression models with BigQuery Explainable AI

Let’s use a boosted tree regression model to predict how much a taxi cab driver will receive in tips for a taxi ride, based on features such as number of passengers, payment type, total payment and trip distance. Then let’s use BigQuery Explainable AI to help us understand how the model made the predictions in terms of global explainability (which features were most important?) and local explainability (how did the model arrive at each prediction?).

The taxi trips dataset comes from the BigQuery public datasets and is publicly available in the table: bigquery-public-data.new_york_taxi_trips.tlc_yellow_trips_2018. 

First, you can train a boosted tree regression model.

  CREATE OR REPLACE MODEL bqml_tutorial.taxi_tip_regression_model
OPTIONS (model_type='boosted_tree_regressor',
         input_label_cols=['tip_amount'],
         max_iterations = 50,
         tree_method = 'HIST',
         subsample = 0.85,
         enable_global_explain = TRUE
) AS
SELECT
  vendor_id,
  passenger_count,
  trip_distance,
  rate_code,
  payment_type,
  total_amount,
  tip_amount
FROM
  `bigquery-public-data.new_york_taxi_trips.tlc_yellow_trips_2018`
WHERE tip_amount >= 0
LIMIT 1000000

Now let’s do a prediction using ML.PREDICT, which is the standard way in BigQuery ML to make predictions without explainability.

  SELECT *
FROM
ML.PREDICT(MODEL bqml_tutorial.taxi_tip_regression_model,
 (
 SELECT
   "0" AS vendor_id,
   1 AS passenger_count,
   CAST(5.85 AS NUMERIC) AS trip_distance,
   "0" AS rate_code,
   "0" AS payment_type,
   CAST(55.56 AS NUMERIC) AS total_amount))

But you might wonder—how did the model generate this prediction of ~11.077?

BigQuery Explainable AI can help us answer this question. Instead of using ML.PREDICT, you use ML.EXPLAIN_PREDICT with an additional optional parameter top_k_features. ML.EXPLAIN_PREDICT extends the capabilities of ML.PREDICT by outputting several additional columns that explain how each feature contributes to the predicted value. In fact, since ML.EXPLAIN_PREDICT includes all the output from ML.PREDICT anyway, you may want to consider using ML.EXPLAIN_PREDICT every time instead.

  SELECT *
FROM
ML.EXPLAIN_PREDICT(MODEL bqml_tutorial.taxi_tip_regression_model,
 (
 SELECT
   "0" AS vendor_id,
   1 AS passenger_count,
   CAST(5.85 AS NUMERIC) AS trip_distance,
   "0" AS rate_code,
   "0" AS payment_type,
   CAST(55.56 AS NUMERIC) AS total_amount),
 STRUCT(6 AS top_k_features))

The way to interpret these columns is:

Σfeature_attributions + baseline_prediction_value = prediction_value

Let’s break this down. The prediction_value is ~11.077, which is simply the predicted_tip_amount. The baseline_prediction_value is ~6.184, which is the tip amount for an average instance. top_feature_attributions indicates how much each of the features contributes towards the prediction value. For example, total_amount contributes ~2.540 to the predicted_tip_amount. 

ML.EXPLAIN_PREDICT provides local feature explainability for regression models. For global feature importance, see the documentation for ML.GLOBAL_EXPLAIN.

Classification models with BigQuery Explainable AI

Let’s use a logistic regression model to show you an example of BigQuery Explainable AI with classification models. We can use the same public dataset as before: bigquery-public-data.new_york_taxi_trips.tlc_yellow_trips_2018.

Train a logistic regression model to predict the bracket of the percentage of the tip amount out of the taxi bill.

  CREATE OR REPLACE MODEL bqml_tutorial.taxi_tip_classification_model
OPTIONS
 (model_type='logistic_reg',
  input_label_cols=['tip_bucket'],
  enable_global_explain=true
) AS
SELECT
  vendor_id,
  passenger_count,
  trip_distance,
  rate_code,
  payment_type,
  total_amount,
  CASE
    WHEN tip_amount > total_amount*0.20 THEN '20% or more'
    WHEN tip_amount > total_amount*0.15 THEN '15% to 20%'
    WHEN tip_amount > total_amount*0.10 THEN '10% to 15%'
  ELSE '10% or less'
  END AS tip_bucket
FROM
  `bigquery-public-data.new_york_taxi_trips.tlc_yellow_trips_2018`
WHERE tip_amount >= 0
LIMIT 1000000

Next, you can run ML.EXPLAIN_PREDICT to get both the classification results and the additional information for local feature explainability. For global explainability, you can use ML.GLOBAL_EXPLAIN. Again, since ML.EXPLAIN_PREDICT includes all the output from ML.PREDICT anyway, you may want to consider using ML.EXPLAIN_PREDICT every time instead.

  SELECT *
FROM
ML.EXPLAIN_PREDICT(MODEL bqml_tutorial.taxi_tip_classification_model,
 (
 SELECT
   "0" AS vendor_id,
   1 AS passenger_count,
   CAST(5.85 AS NUMERIC) AS trip_distance,
   "0" AS rate_code,
   "0" AS payment_type,
   CAST(55.56 AS NUMERIC) AS total_amount),
 STRUCT(6 AS top_k_features))

Similar to the regression example earlier, the formula is used to derive the prediction_value:

Σfeature_attributions + baseline_prediction_value = prediction_value

As you can see in the screenshot above, the baseline_prediction_value is ~0.296. total_amount is the most important feature in making this specific prediction, contributing ~0.067 to the prediction_value, though followed by trip_distance. The feature passenger_count contributes negatively to prediction_value by -0.0015. The features vendor_id, rate_code, and payment_type did not seem to contribute much to the prediction_value.

You may wonder why the prediction_value of ~0.389 doesn’t equal the probability value of  ~0.359. The reason is that unlike for regression models, for classification models, prediction_value is not a probability score. Instead, prediction_value is the logit value (i.e., log-odds) for the predicted class, which you could separately convert to probabilities by applying the softmax transformation to the logit values. For example, a three-class classification has a log-odds output of [2.446, -2.021, -2.190]. After applying the softmax transformation, the probability of these class predictions is [0.9905, 0.0056, 0.0038].

Time-series forecasting models with BigQuery Explainable AI

Explainable AI for forecasting provides more interpretability into how the forecasting model came to its predictions. Let’s go through an example of forecasting the number of bike trips in NYC using the new_york.citibike_trips public data in BigQuery.

You can train a time-series model ARIMA_PLUS:

  CREATE OR REPLACE MODEL bqml_tutorial.nyc_citibike_arima_model
OPTIONS
  (model_type = 'ARIMA_PLUS',
   time_series_timestamp_col = 'date',
   time_series_data_col = 'num_trips',
   holiday_region = 'US'
  ) AS
SELECT
   EXTRACT(DATE from starttime) AS date,
   COUNT(*) AS num_trips
FROM
  `bigquery-public-data.new_york.citibike_trips`
GROUP BY date

Next, you can first try forecasting without explainability using ML.FORECAST:
SELECT
  *
FROM
  ML.FORECAST(MODEL bqml_tutorial.nyc_citibike_arima_model,
              STRUCT(365 AS horizon, 0.9 AS confidence_level))

This function outputs the forecasted values and the prediction interval. Plotting it in addition to the input time series gives the following figure.

But how does the forecasting model arrive at its predictions? Explainability is especially important if the model ever generates unexpected results.

With ML.EXPLAIN_FORECAST, BigQuery Explainable AI provides extra transparency into the seasonality, trend, holiday effects, level (step) changes, and spikes and dips outlier removal. In fact, since ML.EXPLAIN_FORECAST includes all the output from ML.FORECAST anyway, you may want to consider using ML.EXPLAIN_FORECAST every time instead.

  SELECT
  *
FROM
  ML.EXPLAIN_FORECAST(MODEL bqml_tutorial.nyc_citibike_arima_model,
                      STRUCT(365 AS horizon, 0.9 AS confidence_level))

Compared to the previous figure which only shows the forecasting results, this figure shows much richer information to explain how the forecast is made.  

First, it shows how the input time series is adjusted by removing the spikes and dips anomalies, and by compensating the level changes. That is:

time_series_adjusted_data = time_series_data - spikes_and_dips - step_changes

Second, it shows how the adjusted input time series is decomposed into different components such as both weekly and yearly seasonal components, holiday effect component and trend component. That is

time_series_adjusted_data = trend + seasonal_period_yearly + seasonal_period_weekly + holiday_effect + residual

Finally, it shows how these components are forecasted separately to compose the final forecasting results. That is:

time_series_data = trend + seasonal_period_yearly + seasonal_period_weekly + holiday_effect

For more information on these time series components, please see the documentation here.

Conclusion

With the GA of BigQuery Explainable AI, we hope you will now be able to interpret your machine learning models with ease. 

Thanks to the BigQuery ML team, especially Lisa Yin, Jiashang Liu, Amir Hormati, Mingge Deng, Jerry Ye and Abhinav Khushraj. Also thanks to the Vertex Explainable AI team, especially David Pitman and Besim Avci.

In the past few years, a series of new technologies and regulatory changes has been transforming Brazil’s financial industry. The concept of blockchain added security and agility to financial transactions. The open banking system being deployed by the country’s Central Bank (BC) allows for platform integration and data sharing -with the user’s consent- between financial institutions. Recently, the launch of Pix, also by the BC, has shaken the market by creating a new payment method that is instant, free for individuals and 24/7.

Since 2018, the startup Bit Capital has been working on the development of 100%-digital financial solutions in the cloud to help its clients adapt to this new scenario in a convenient way, without the need to build an infrastructure for that or hiring different providers. Pix was not the exception.

In less than 3 months, the team was able to build and go live with a solution that can be used by both direct participants (i.e. those with banking licenses granted by BC) and indirect participants (i.e. companies depending on direct participants to offer payments on Pix) through Bit Capital’s platform.

Besides this differential, Pix and the startup’s other solutions are based on blockchain and Google Cloud’s cloud, ensuring greater security, scalability and availability for customers and allowing for an easy integration between Bit Capital’s platform’s solutions and those from other companies.

“Now we have a platform with an API and various microsservices, allowing clients to connect and develop their own financial product without having to start from scratch.”

—Francesco Miolo, CFO, Bit Capital

A robust structure to handle Pix’s high demand

Bit Capital was established with a certain urgency to develop its platform. The idea was well-developed and customers were interested. The fast deployment of Google Cloud’s tools was one of the main factors that attracted the company to use it as a basis for its infrastructure.

“We managed to deliver everything we have today in Google Cloud with a small team. That was another challenge: being able to grow with a few people,” says Juliano Souza, the startup’s head of IT infrastructure. “We sought other cloud partners, but they had a steep curve. We chose Google Cloud because we needed quick, quality scaling.”

The same thing happened when they built the solution for Pix, despite the specific challenges involved. The BC had performance requirements that led the company to spend some time experimenting until they reached the best suite of tools to meet those requirements. The startup wanted to create a unique architecture that could help both large and small customers and be integrated to the platform’s other microservices.

With the support from Google Cloud’s team to answer doubts and make the best decisions, the solution was built in a few months, at a cost about two-thirds lower than other providers.

The solution’s architecture is based on apps running in Docker in Google Kubernetes Engine (GKE), with interconnected microservices. The blockchain system runs on Compute Engine, its rows are managed in Pub/Sub and Dataflow, and persistent data, in Cloud SQL. Cloud Interconnect is used for the connection with BC. Cloud KMS and Secrets Management store the company’s pre-credentials. All of this is supported by Cloud Load Balancing for load balancing and autoscaling.

According to the team, GKE was essential for the solution’s success. Using infrastructure as code in the tool made uploading of a group of microservices significantly easier. Developers are able to help set up this environment, which has helped spread the DevOps culture in the team. Besides orchestrating and integrating apps, GKE also provides an elastic structure to handle demand peaks and visibility to monitor internal components.

“Google Kubernetes Engine was the only way to ensure availability, observability and elasticity for all clients, whether small, middle-sized or large.”

—Juliano Souza, Head of IT Infrastructure, Bit Capital

Nowadays, the solution’s environment has 20 clusters with over 1,500 pods – 250GB in data per month, providing a robust structure to support a service involving periods of intense demand such as Black Friday.

Ease to monitor, fix and improve

Just 10 days after Pix’s official launch date, the company had its first test: Black Friday. This allowed a major e-commerce customer to test the scale and see the success of the architecture that had been built. “It worked great regarding what the cloud could deliver. And we found what we needed to fix very quickly. Operations [formerly Stackdriver], in particular Cloud Trace, showed us clearly what needed to be done to improve performance,” Souza explains.

Using Operations added reliability by putting deliveries into production. Checking Cloud Trace to see if there were any performance issues and the exact point where they were happening became routine for Bit Capital’s developers. Google Cloud’s security tools and Google Safety Center provided the resources needed to monitor and secure the environment, with automatic data encryption at rest and in transit.

“Google Cloud has security as a premise. When we upload any kind of component, like a database or a virtual machine, the drive is encrypted by default. With other providers, you must specify that you want it encrypted.

”—Juliano Souza, Head of IT Infrastructure, Bit Capital

The easy service monitoring and management accelerates product and technology development because the team no longer needs to worry about infrastructure. Automated management allows professionals to spend more time on new projects and the company’s business. Also, the deployment of services in a Google Cloud multi-region impacts on customer experience, providing high availability for their solutions.

In the coming months, Bit Capital aims to ramp up service usage and the creation of new projects in Google Cloud by adding more customers to Pix’s solution and Banking as a Service (BaaS) solutions. Anthos will be incorporated to the tool suite to make it easier to connect apps with the customers’ on-prem environments. And the deployment of open banking has the potential to be a business driver for the company.

“We joke that we’re already doing open banking, because we have various connections with different providers, which allows us to offer an integrated solution,” says Francesco Miolo, the startup’s CFO. “With the arrival of the new regulations, something we are waiting for since we started out, we will be able, through our platform, to take our customers to the open finance ecosystem, enabling the development of disruptive business models.”