Customer churn is to find whether a customer will leave a particular service or not. Effective churn rate prediction is an essential challenge for the service industry as the cost of earning new customers is a lot more than sustaining existing ones. Preventive actions, new marketing strategies, and long term service contracts can be made if the churners are identified at an early stage.

In this proposal, we discuss the application of hybrid auto encoder attention models to calculate the churn score of the automobile service consumers and provide the dynamic personalized discounting at the right stage to subvert churn out. We also show the implementation of reinforcement learning to update and optimize the discounting portfolio to minimize the loss by targeting the high potential customers only. Traditionally available classification and scoring algorithms require manual feature extraction and cannot handle skewed datasets. However, the hybrid model can produce better results even for fewer training sets. Autoencoder network represents the data into a latent space while the attention layer simultaneously works to focus on highly contributing features for target prediction.


With this concise understanding of transactional data, the industry professionals can have better estimations on when existing customers might be open to considering upgrading to premium vehicles and when they are on the verge to churn out. Hence, they can act accordingly.

 
 

Outline/Structure of the Experience Report

- Background research of data-driven growth in the Automotive sector

- Description of data pre-processing and manipulation.

- A detailed framework to calculate the churn score of each customer through hybrid deep learning model.

- Customer retention strategy via dynamic discounting and targeted servicing through improved methods.

- Application of reinforcement learning for self-optimization of strategy to maximize the output of discounting.

Learning Outcome

Through this talk, attendees will understand the various challenges of the service industry that can be solved by the application of deep learning and how data-driven growth can bring disruptive improvement sales and marketing. By the end of the session, participants will learn about the implementation of advance hybrid algorithm i.e. Attention Autoencoder Network which does not require manual feature engineering that is usually a challenge with traditional classification algorithms. They will also get the theoretical/mathematical understanding of reinforcement learning and its application in dynamic optimization.

Target Audience

Anyone interested in state of the art deep learning models or working on churn reduction using customer data analytics

Prerequisites for Attendees

Basic knowledge of python, statistics and machine learning. Prior Knowledge of deep learning is advantageous but not necessary.

Slides


schedule Submitted 1 year ago

Public Feedback

    help