tomsriddle/rl-email-campaign repository overview

⁠Email Campaign Conversion Rates

⁠Overview

This repository provides a prototype implementation of improving conversion rates for email campaigns using Reinforcement Learning

⁠Local Development Environment used for running image

• Apple Mac M1 chip
• Sonoma 14.1.2
• Docker Desktop for Mac 4.26.1 (131620)

⁠Docker

⁠Pull Image

To pull an image use the following

docker pull tomsriddle/rl-email-campaign:1.0

After pulling the image check that it is present using following

docker image ls

⁠Run Image

To run the image use following

docker run -p <host port>:8786 -v <host path>:/workspace/shared-data -e data-folder=/workspace/shared-data/ -e training-data-file=email_campaign_data.csv "tomsriddle/rl-email-campaign:1.0" 

Note: At the moment the image comes packaged with the needed Q Tables and the Campaign Data used for Training. So you can skip the file passing

⁠Docker Run Example

⁠API Usage

Following APIs exposed

⁠Get Next State

This provides next action that can be taken on the basis of

POST http://localhost:8788/get-next-action

Request Body (all attributes are mandatory)
--------------------------------------------------------
{
        "state": [2,0,1,4,3,1,1],
        "action": 4
}

Response Body
--------------------------------------------------------

{
    "next_action": 0
}

⁠Troubleshooting

• As a part of running from local or through docker image, we have to pass arguments for the folder where the training data is.