Customer service machine learning models

Increase chat bot, web and app accuracy to support greater customer satisfaction.

New customer technologies such as chat bots have become mainstream in customer support. However, they are only as effective as the engine behind them. An insufficient engine can lead to unproductive chat bot conversations that are redirected to a human assistant, reducing efficiency and the quality of the experience to the customer.

Machine Learning (ML) models can facilitate chat bot effectiveness to enable improved responses and resolution time for customer queries, as well as higher customer satisfaction scores.

Customer service machine learning models

Solutions

Persistent Systems

Persistent Systems partners with customers on their data-driven continuous transformations. Persistent Systems Banking FAQ Intent Matching ML model can be deployed using Amazon SageMaker and made accessible to business applications such as a bank’s chat bot via REST API, using AWS API Gateway and Lambda services.

The model is trained on varying utterances and FAQs about banking services and predicts the closest intent for a given question. According to Persistent Systems, benchmarked against the chat bot's intent selection results, the Persistent Systems model typically shows an absolute improvement of 8 to 10 percent in terms of accuracy for the prototype that was built.

Persistent Systems Banking FAQ Intent Matching ML model works directly with Amazon Sagemaker. Here’s how it works:

Persistent Systems Banking FAQ
AWS Marketplace

AWS Marketplace is a digital catalog with thousands of software listings from independent software vendors that make it easy to find, test, buy, and deploy software that runs on AWS.

Financial services customers using AWS

CapitalOne
FICO
National Bank of Canada
Stripe
Have questions? Have tips?

We're here to help you get started with AWS Marketplace. Ask for or give advice on the AWS Marketplace discussion forum.

Have questions? Have tips?

We're here to help you get started with AWS Marketplace. Ask for or give advice on the AWS Marketplace discussion forum.