E-commerce Platform Designed for Continuous Optimization and Personalization

https://drive.google.com/file/d/18tZeFa3DHdCUpjKr3w10ey7cpoJXCvfD/view?usp=drive_link

Ability of an e-commerce company to collect, synthesize and utilize data can be vital to its survival. The degree to which a company has the ability to gather data about sources of conversion is proportional to their ability to allocate advertising / implementation budget effectively. Measurement and optimization of user flow on a website is equally important as it can deliver a measurable increase in user loyalty, revenue and profits. Similarly, it can reveal that numerous improvements, although looking good ”on the paper” does not work well in the real situations. In this thesis, we develop an e-commerce solution for a real world company, but applicable more generally. In addition to the standard e-commerce features, the platform is able to collect data about its usage. We utilize the data gathering to set up experiments on the platform with contextual multi armed bandits algorithm. We develop a recommendation system based on collaborative filtering and set up an experiment to evaluate it’s real world performance in comparison to a list of previously viewed products. The platform is connected to a business intelligence dashboard to enable exploration of the data, to support its management in making informed tactical & strategic decisions. The platform is developed with Blazor, which is an emerging technology which enables usage on C# code in the browser with compilation to WebAssembly instead of JavaScript, we describe the experience with the advantages and challenges of using this technology.