AI Case Study
AXA used deep neural networks to increase the predictability of a customer large traffic accident from 40% to 78%
AXA wanted to reduce payout costs by better predicting the 1% of their customers that would have large traffic accidents resulting in payouts over $10,000. Using deep neural networks on over 70 variables, such as age and region of the drivers address, they increased the accuracy of prediction to 78% versus less than 40% with random forests.
Industry
Financial Services
Insurance
Project Overview
"Toward that goal, AXA’s R&D team in Japan has been researching the use of machine learning to predict if a driver may cause a large-loss case during the insurance period. Initially, the team had been focusing on a traditional machine-learning technique called Random Forest. Random Forest is a popular algorithm that uses multiple Decision Trees (such as possible reasons why a driver would cause a large-loss accident) for predictive modeling. Although Random Forest can be effective for certain applications, in AXA's case, its prediction accuracy of less than 40% was inadequate."
"In contrast, after developing an experimental deep learning (neural-network) model using TensorFlow via Cloud Machine Learning Engine, the team achieved 78% accuracy in its predictions. This improvement could give AXA a significant advantage for optimizing insurance cost and pricing, in addition to the possibility of creating new insurance services such as real-time pricing at point of sale."
Reported Results
Predict “large-loss” traffic accidents with 78% accuracy (compared to 39% with previous models). This would allow them to better optimise pricing of premiums.
Technology
"AXA entered these features into a single vector with 70 dimensions and put it into a deep learning model in the middle. The model is designed as a fully connected neural network with three hidden layers, with a ReLU as the activation function. AXA used data in Google Compute Engine to train the TensorFlow model, and Cloud Machine Learning Engine’s HyperTune feature to tune hyperparameters."
Function
Strategy
Strategic Planning
Background
"Approximately 7-10% of AXA’s customers cause a car accident every year. Most of them are small accidents involving insurance payments in the hundreds or thousands of dollars, but about 1% are so-called large-loss cases that require payouts over $10,000. As you might expect, it’s important for AXA adjusters to understand which clients are at higher risk for such cases in order to optimize the pricing of its policies."
Benefits
Data
"...there are about 70 values as input features including the age range of the driver, the region of the driver's address, the annual insurance premium rang and age range of the car."