3 Mins Read

scriptcheck

Voiced by Amazon Polly

intro

Thank you Bhavesh.

Hello All, I am Dev Pathi from Credit Saison and I head the Technical team (CTO) here.

Before talking about how we leveraged Amazon Sagemaker service for our infrastructure, let me quickly share what Credit Saison is.

We were incorporated in 1951 and headquartered in Tokyo with businesses in Credit service, leasing and finance, real estate, and entertainment.

Credit Saison India is a subsidiary of its Japanese parent We set up the Indian entity 4 years back with the intention of being a Technology-led NBFC. Fast forward to today, we have successfully deep-routed ourselves into the eco-system with a substantial loan book size powered by our in-house tech team. Our USP has been about integrating and scaling digital partnerships and has given us the momentum to go direct to market (where we need plenty of AI/ML).

We have over 400 employees across India of which the tech team alone is close to 100 folks. We rely on partners like CloudThat to help us with skilled resources.

Our move to Cloud with AWS

Considering our global focus on moving ahead with digital transformation across all the operations, Year 2019, we initiated the project to migrate about 40 core peripheral systems, including credit screening, to Amazon Web Services (AWS). To accelerate digitization, new services like digital marketing infrastructure and scoring services will be developed in a cloud-first manner, based on AWS. Decision to move to AWS was mainly driven by their extensive track record of implementations in Financial sector.

Considering the key factors among a range of cloud services: cost, fault tolerance, track record of implementation in financial institutions, and number of services offered, AWS emerged as our choice of cloud provider. In 2019, Credit Saison also began the development of a payment demand system using Amazon Connect to automate 200,000 calls per month.

The global drive is to migrate 80% of all core peripheral systems to AWS by 2025, and expect to reduce the IT costs by 3.8 billion yen over the next 10 years.

There are a lot of AWS services that have come to our rescue in getting our IT costs optimized. To name a few
Amazon EC2s has been our go-to compute

Amazon Connect, as I mentioned our automation for call

Amazon Polly has been by our side providing the capabilities of text to speech

AWS Lambda has been used across applications for multiple background processing

And now Amazon Sagemaker will take our ML models from development to production

Now that I have mentioned Amazon Sagemaker, let me talk about the challenges we were facing in our fraud detection Pipeline

Currently, we are doing a lot of preprocessing using a fleet of AWS Lambda functions and the models are trained on physical laptops. While it is doing its job, we were struggling to handle a large dataset due to limited hardware on machines. We were having problems optimizing our model building and data preprocessing pipelines for fraud detection as well as risk assessment.

In one of my conversations with AWS, they routed me to CloudThat and I should really appreciate the time and effort that the CloudThat team has put to come up with the solution and the help they have offered in implementing the same.

The implementation has been already discussed in depth by Bhavesh, however, let me talk to you about my personal key takeaways from the solution

 

  1. The word impossible literally means I M Possible

Let me give an example, as we are processing a lot of data from credit score providers, not every time we receive the data in a readable format. One such hurdle we had in this project, and I heard from my team that this would not be possible. Kudos to the CloudThat team, they integrated AWS Lambda and Amazon Sagemaker so seamlessly that the team did not even have to lift a finger to modify/transform the response.

 

  1. It is more relaxing to be Cloud Native than a Hybrid

In the previous system, I had to rely on individuals to build and deploy models while the preprocessing was done on AWS. With the solution implemented, no dependency on individuals. The individuals can now focus on monitoring the model performance rather than worrying about the data drift

 

  1. Development to Deployment is faster

Like Bhavesh Mentioned, my deployments are 50% faster than the older system

 

  1. Increased observability

In the previous system, I did not have any view of what is happening with my ML ecosystem. With the current system at any given point in time, I can check how a particular model is performing.

 

Overall, I would term this project a successful implementation of the MLOps pipeline for Risk Assessment and Fraud Detection by synergizing multiple AWS Services.

To close, with help of Amazon Sagemaker and CloudThat’s expertise in ML Workflows, I am able to reduce not only the manual dependency but also the purchase of high-configuration laptops along with an increase in the speed from data to delivery.

Thank you for your time Back to Bhavesh

Get your new hires billable within 1-60 days. Experience our Capability Development Framework today.

  • Cloud Training
  • Customized Training
  • Experiential Learning
Read More

FAQs

1. Question

ANS: –  

WRITTEN BY Prarthit Mehta

Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book

Share

Comments

    Click to Comment

Get The Most Out Of Us

Our support doesn't end here. We have monthly newsletters, study guides, practice questions, and more to assist you in upgrading your cloud career. Subscribe to get them all!