# Fast Online "Next Best Offers" using Deep Learning

## TL;DR

This paper introduces iPrescribe, a scalable, low-latency system for real-time next-best-offer recommendations using ensemble deep learning models, achieving under 40 milliseconds latency.

## Contribution

The paper presents a novel architecture and optimization techniques for deploying recurrent LSTM networks efficiently in real-time recommendation systems.

## Key findings

- Achieved 38 ms latency at the 90th percentile
- Compared different streaming technology stacks
- Demonstrated scalable real-time recommendation performance

## Abstract

In this paper, we present iPrescribe, a scalable low-latency architecture for recommending 'next-best-offers' in an online setting. The paper presents the design of iPrescribe and compares its performance for implementations using different real-time streaming technology stacks. iPrescribe uses an ensemble of deep learning and machine learning algorithms for prediction. We describe the scalable real-time streaming technology stack and optimized machine-learning implementations to achieve a 90th percentile recommendation latency of 38 milliseconds. Optimizations include a novel mechanism to deploy recurrent Long Short Term Memory (LSTM) deep learning networks efficiently.