In a perfect cloud world, you would host all your applications in containers running on Kubernetes and Istio, benefitting from the portability and improved resource utilization of containers, plus a robust orchestration platform with advanced application management, networking, and security functionality. This is easy to do if you’re developing a new application, but it can be hard for existing applications to take advantage of those capabilities.

Many of the applications that you may want to move to the cloud have been around a long time, and you may not have the application-specific knowledge that would be required to rewrite them to be more cloud-native—or it would be incredibly time-consuming to do so.

Another option is to lift-and-shift to a virtual machine (VM) hosting platform like Compute Engine, but that means you still need to maintain the VMs. Even if you’re not able to fully modernize an existing app, it would still be great to get some of the benefits of containers and Kubernetes.

What is Migrate for Anthos?

Enter Migrate for Anthos, a fast and easy way to modernize your existing applications with a service that encapsulates them in a container. Moving your physical servers or existing VMs into Kubernetes containers gives you crucial portability and resource utilization benefits without having to rewrite the underlying application.

Since Migrate for Anthos is built for Google Kubernetes Engine (GKE), you also automatically capture the scaling and flexibility benefits of a managed Kubernetes environment in the cloud. Migrate for Anthos recently became generally available.

Converting an application with Migrate for Anthos happens in two phases. First, it creates a generic container wrapper around your application that makes it seem like it is still running in a full VM environment. Then, you launch Migrate for Anthos software on your Kubernetes cluster that runs the containerized application.

You can find more details about this in the documentation and in our blog post: Migrating from Compute Engine to Kubernetes Engine with Migrate for Anthos.

As the name suggests, Migrate for Anthos works with Anthos GKE. However, you can also use Migrate for Anthos with only GKE—all it requires is your application and a GKE cluster running the Migrate for Anthos software. 

Getting started with Migrate for Anthos

Migrate for Anthos works with a variety of workloads, but not all. It’s particularly adept at migrating legacy applications, stand-alone applications, and monolithic applications. As you start the modernization process, here are some questions to ask to determine whether to use Migrate for Anthos with your applications:

1. Should this app be in the cloud?
By its nature, the cloud may not be able to support some characteristics of your on-prem environment, such as geography and legal compliance. The best way to find out whether the cloud will work for each of your applications is to plan out a full migration. That will allow you to identify groups of applications that can benefit from cloud offerings such as a global network and ease of resizing resources. After that, try out a proof of concept by testing the apps in the cloud to see if it fits your business needs.

2. Should this app be in Kubernetes?
Containerizing an application simplifies workload administration, improves scalability (both up and down), and increases host utilization. Kubernetes orchestrates the containers and GKE handles node upgrades, while add-ons like Istio let you manage network and security policies independently of your application.

With those advantages, it’s easy to think that containers are always the right way to go, but there are some cases where it may make sense to stick with VMs. Strict hardware requirements, specialized kernel modules, and license constraints may be harder to run with containers, negating their advantages.

3. Should this app migration use Migrate for Anthos?
Migrating your apps or workloads to the cloud isn’t just about shifting where the compute resources run; it’s also an opportunity to modernize them with containers. Using Migrate for Anthos (or Migrate for Compute Engine) gives you the ability to get your workloads in the cloud quickly, with minimal upfront downtime that’s easy to plan for. 

However, even if you use the Migrate for Anthos wrapper, your application is still the same application. The benefits of the modern platform may not outweigh a legacy application and a rewrite may be the only way to meet your business needs. There are also some specific services from your VM that may not work with Migrate for Anthos, for example licensing requirements.

Migrate for Anthos can also be the first step in a larger migration effort. Once you’ve migrated the application to GKE, you can gradually break up a monolithic app into microservices by manually rewriting parts. Spreading out the migration effort gets you in the cloud sooner, giving you more time to modernize.

Next steps

A successful modernization starts with creating a full migration plan, testing the workloads, and monitoring them. You can experience the benefits of modernization with Migrate for Anthos by picking a small workload and trying it out for yourself!

Many of our customers want to know how to choose a technology stack for solving problems with machine learning (ML). There are many choices for these solutions available, some that you can build and some that you can buy. We’ll be focusing on the build side here, exploring the various options and the problems they solve, along with our recommendations. 

The best ML applications are trained with the largest amount of data

But first, keep in mind an important concept: the quality of your ML model improves with the size of your data. Dramatic ML performance and accuracy are driven by improvements in data size, as shown in the graph below. This is a text model, but the same principles hold for all kinds of ML models.

The X axis represents the size of the data set and the Y axis is the error rate. As the size of the data set increases, the error rate drops. But notice something critical about the size of the data set — the x-axis is2^20, 2^21, 2^ 22, etc. In other words, each new tic here is a doubling of the data set size. To get a linear decrease in your error rate you need to exponentially increase the size of your data set. 

The blue curve in the graph represents a slightly more sophisticated ML model than the orange curve. Suppose you are deciding between two choices: create a better model or double the data set size. Assuming that these two choices cost the same, it’s better to keep gathering more data. It’s only when improvements due to data size increases start to plateau that it becomes necessary to build a better model. 

Secondly, ML systems need to be retrained for new situations. For example, if you have a recommendation system in YouTube and you want to provide recommendations in Google Now, you can’t use the same recommendations model. You have to train it in the second instance on the recommendations you want to make in Google Now. So even though the model, the code, and the principles are the same, you have to retrain the model with new data for new situations. 

Now, let’s combine these two concepts: you get a better ML model when you have more data, and an ML model typically needs to be retrained for a new situation. You have a choice of either spending your time building an ML model or buying a vendor’s off-the-shelf model. 

To answer the question of whether to buy or whether to build, first determine if the buyable model is solving the same problem that you want to solve. Has it been trained on the same input and on similar labels? Let’s say you’re trying to do a product search, and the model has been trained on catalog images as inputs. But you want to do a product search based on users’ mobile phone photographs of the products. The model that was trained on catalog images won’t work on your mobile phone photographs, and you’d have to build a new model. 

But let’s say you’re considering a vendor’s translation model that’s been trained on speeches in the European Parliament. If you want to translate similar speeches, the model works well as it uses the same kind of data. 

The next question to ask: does the vendor have more data than you do? If the vendor has trained their model on speeches in the European Parliament but you have access to more speech data than they have, you should build. If they have more data, then we recommend buying their model. 

Bottom line: buy the vendor’s solution if it’s trained on the same problem and has access to more data than you do. 

Technology stack for common ML use cases

If you need to build, what is the technology stack you need? What are the skills your people need to develop? This depends on the type of problem you are solving.  There are four broad categories of ML applications: predictive analytics, unstructured data, automation, and personalization. The recommended technology stack for each is slightly different. 

Predictive analytics

Predictive analytics includes detecting fraud, predicting click-through rates, and forecasting demand. 

Step one: build an enterprise data warehouse
Here, your data set is primarily structured data, so our recommended first step is to store your data in an enterprise data warehouse (EDW). Your EDW is a source of training examples and product histories tracked over time, and can break down silos and gather data from throughout your organization.

Step two: get good at data analytics
Next, you’d build a data culture, get skilled at data analytics, start to build dashboards, and enable data-driven decisions. At this point, you have all of the data and you know which pieces are trustworthy. 

Step three: build ML
From your EDW, you can build your models using SQL pipelines. We recommend using BigQuery ML when doing ML with the data in your EDW. If you want to build a more sophisticated model, you can train TensorFlow/Keras models on BigQuery data. A third option is AutoML tables for state-of-the-art accuracy and for building online microservices.

Unstructured data

Examples of how our customers use ML to gain insights from unstructured data include annotating videos, identifying eye diseases, and triaging emails. Unstructured data can include videos, images, natural language, and text. Deep learning has revolutionized the way we do ML on unstructured data, whether you’re looking at language understanding, image classification, or speech-to-text. 

For unstructured data, the models you use will  employ deep learning. Here, the ROI heavily favors using AutoML. The amount of time that you’d spend trying to create a new ML model from scratch is almost never worth it. You can spend your money more effectively collecting more data than trying to get a slightly better model. Regardless of the type of unstructured data, our recommendation is to use AutoML for small and medium size data sizes.

But AutoML has a limit to scale. At some point, the size of your data set is going to be so large that architecture search is going to get really expensive. At that point, you may want to go to a best-of-breed model with custom retraining from TensorFlow Hub, for example.  If you have data sets that are in the millions of examples, you can build your own custom neural network (NN) architectures. But determine if your data set size has started to plateau, by plotting a graph similar to the one at the top of this post. Build a custom NN architecture only after you’ve plateaued, where increasing amounts of data won’t give you a better model. 

Automation

Some examples of how customers are using ML for automation include scheduling maintenance, counting retail footfall, and scanning medical forms. The key thing to keep in mind as you pick a technology stack for these problems is that you’re not building just one ML model. If you want to schedule maintenance orwant to reject transactions, for example, you’ll need to train multiple linked models. 

Instead of individual models, think in terms of ML pipelines, which you can orchestrate using all of the technologies already mentioned. Then you have three choices for operationalizing, with three levels of sophistication.

1. Vertex AI has turnkey serverless training and batch/online predictions. This is what is recommended for a team of data scientists. .
2. Deep Learning VM Image, Cloud Run, Cloud Functions or Dataflow feature customized training and batch/online predictions. This is what is recommended if the team consists of  data engineers and  scientists.
3. Vertex AI Pipelines are fully customizable and recommended for organizations with separate ML engineering and data science teams.

When doing automation, the individual models that you chain together into a pipeline will be a mix – some will be prebuilt, some will be customized, and others will be built from scratch. Vertex AI, by providing a unified interface for all these model types, simplifies the operationalization of these models.

Personalization

ML application examples of personalization include customer segmentation, customer targeting, and product recommendations. For personalization, we again recommend using an EDW, because customer segmentation uses structured marketing data. For product recommendations, you will similarly have prior purchases and web logs in your EDW., You can power clustering applications, or recommendation systems like matrix factorization, and create embeddings directly from your EDW for sophisticated recommendation systems.

For specific use cases, choose the technology stack based on your data size and scope. Start with BigQuery ML for its quick, easy matrix factorization approach. Once your application proves viable and you want a slightly better accuracy, then try AutoML recommendations. But once your data set grows beyond the capabilities of AutoML recommendations, consider training your own custom TensorFlow and Keras models. 

To summarize, successful ML starts with the question, “Do I build or do I buy?” If an off-the-shelf solution exists that was trained with similar data and with access to more data than you have, then buy it. Otherwise build it, using the technology stack recommended above for the four categories of ML applications.

Learn more about our artificial intelligence (AI) and ML solutions and check out sessions from our Applied ML Summit on-demand.

Google Cloud results

• Helps enable instant document approval with optical character recognition by Vision API
• Processes 100,000 documents in 20 minutes with automated document processing product Recognic, powered by Vision API and Apigee
• Helps increase the number of applications processed by 30% within the same timeframe

The insurance landscape in India has seen significant changes in recent years with the adoption of new technology. As one of the major insurance providers in the country, ICICI Prudential Life Insurance has aimed to lead in this transformation journey. “There has been a data explosion across India over the past few years, together with a high mobile penetration rate. Today, about 60% of our customers approach us via mobile, for example, which was certainly not the case before,” says Alpesh Karnik, SVP, IT, at ICICI Life Insurance.

Consumer expectations have also evolved, with easier access to information and online services. “Consumers today are more informed on the importance of investing in insurance products, so there’s much more of a pull factor when it comes to sales, but they also want to be able to get these products quickly and easily,” adds Alpesh. To meet the demands of these consumers, ICICI Prudential Life Insurance realized it needed to make its processes even faster and more efficient. Looking to upgrade its infrastructure, the company turned to Google Cloud.

“The biggest benefit of using Recognic and Vision API is that it eliminates the initial waiting time, which can result in drop-offs. Now customers can know immediately whether their documents are sufficient, or if they need to revise or submit any others.”—Alpesh Karnik, SVP, IT, ICICI Prudential Life Insurance

Serving customers better by speeding up processes with Google Cloud

ICICI Prudential Life Insurance’s distributors were already using tablets to input customer data faster and more efficiently, but many of the company’s solutions still required a team at the back end to manually sift through documents for approval. This meant that customers needed to wait five or six hours, or sometimes until the next working day, to know if their documents were approved or needed revision.

That all changed after partnering with Google Cloud Premier Partner Searce to take advantage of its AI/ML powered automated document processing product Recognic, which is built on Google Cloud. Developed using the optical character recognition (OCR) capabilities of Cloud Vision, Recognic reads, understands, and validates documents at scale, enabling organizations that handle massive amounts of paperwork to digitize these documents and then accurately store and index them.

“Google Cloud has cut down the middle- and back-office work, leading to a 30% increase in the number of applications we can process in the same time span without the need for additional resources.”—Alpesh Karnik, SVP, IT, ICICI Prudential Life Insurance

“In the case of ICICI Prudential, the biggest benefit of using Recognic and Vision API is that it eliminates the initial waiting time, which can result in drop-offs. Now customers can know immediately whether their documents are sufficient, or if they need to revise or submit any others,” Alpesh adds.

Alpesh explains that if the details on the application form match the documents provided, the case doesn’t need to go to the underwriter for further checks and can go directly to policy issuance. “Google Cloud has cut down the middle- and back-office work, leading to a 30% increase in the number of applications we can process in the same time span without the need for additional resources.”

ICICI Prudential Life Insurance is also working with Searce to build deep learning models into Recognic so that it can overcome template barriers and input data from a variety of forms. This is particularly helpful for financial and medical documents underwriting because unlike a passport or driving license, financial documents have a higher structural complexity.

As customer data becomes more important in the work of ICICI Prudential Life Insurance, so does protecting it, and the company is taking every measure to safeguard the security and privacy of its customers’ information. “Details of customers’ contactability are automatically removed by Google Cloud after processing is complete. This step in the workflow gives us the confidence that data is not stored at any level of the optical character recognition process,” says Alpesh.

Partnering with the right teams for dedicated support

In achieving the best solution for its business goals, ICICI Prudential Life Insurance recognizes the importance of its decision to work with partners that truly understand the insurance business. “There are many intricacies involved in this business, and it’s clear that both Google Cloud and Searce really took the time to understand our underwriting processes before coming up with a solution,” says Alpesh. He adds that during the implementation process, all findings were well documented and queries were responded to quickly.

“We didn’t want to take any shortcuts deploying Recognic, but at the same time, we didn’t want to draw out the implementation process. The excellent support from both Google Cloud and Searce throughout the journey was reassuring for us as they were always thinking ahead.”

Future-proofing the organization through machine learning and AI

In the coming years, Alpesh foresees the insurance industry to be even more agile than it is today. “I doubt elaborate processes such as underwriting or operations checks will need to be done manually in the future. Everything will be done through machine learning and AI.” In light of this, ICICI Prudential Life Insurance is doing everything it can to prepare, as customers’ expectations are set to keep evolving. “We have to be prepared for the future, and I believe that with Google Cloud, we can do it.”

About ICICI Prudential Life Insurance

ICICI Prudential Life Insurance aims to lead the Indian insurance field through quality products and a hassle-free claim settlement experience. A customer-centric company, it offers long-term savings and protection plans to meet customers’ needs at every stage of life.Industries: Financial Services & InsuranceLocation: India

About Searce

Searce is a niche cloud consulting business with futuristic tech in its DNA, focused on “realizing the Next in the Now” for its clients. Specializing in cloud data engineering, AI/ML, and ad