I couldn’t sit quietly on my idea for long; the urge to take action grew stronger with each passing day. My mind was fixated on conducting research in Edutech and implementing a more advanced level of personalization than what currently existed. Despite the exciting AI journey that lay ahead, my primary focus was on obtaining a suitable dataset to kickstart my work on personalization. That’s when I stumbled upon a Kaggle competition featuring RIIID’s dataset, and I knew it was the perfect opportunity to get started.

This project focuses on implementing the query, key, and value computation for knowledge tracing, inspired by the paper “Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing.” The objective is to enhance the existing knowledge tracing models by improving the computation of queries, keys, and values.

This project focuses on the implementation of an enhanced architecture, SAINT: Separated Self-Attentive Neural Knowledge Tracing, which builds upon the existing SAINT model. The SAINT architecture aims to improve knowledge tracing in educational settings by leveraging self-attention mechanisms.

In this project, I utilized the powerful forecasting library FBProphet to analyze and predict trends in the Indian stock market. By leveraging FBProphet’s advanced time series analysis capabilities, I aimed to uncover valuable insights and make informed predictions.