Interactive Supervised Machine Learning Model Evaluation Using D3

Egill Gunnarsson
Advisor: Dr. Rafal Angryk

The evaluation of a supervised machine-learning model is one of the most important phases in its life cycle. Although there are numerous evaluation metrics, each of which provides a different insight into a model's performance, it can sometimes be challenging to find the appropriate ones that fit the problem in hand. Including the imbalance ratio as an extra variable makes the evaluation process even more difficult. Therefore, I implemented a web application to intuitively evaluate models' performance based on their confusion matrices and given imbalance ratios. This project is an online, interactive application of the contingency space concept recently proposed by Ahmadzadeh et al. (2021). Inspired by this concept, my web application allows the user to visually evaluate their pre-trained supervised models. A side-by-side graphical representation of multiple metrics is provided for a comparison between metrics scores. Confusion matrices are evaluated on such metrics as accuracy, precision, F1 score, and recall. Additionally, the user can load their own customized metrics as well. The visualization is based on contour plots that correlate to each metrics score in relation to true positive and true negative rates and imbalance ratios.

This application uses technologies such as D3.js, Python, JavaScript, HTML, CSS, Flask, and JSON. Each metric’s score is generated in the backend using Python, based on an imbalance ratio. Information is sent to and from the backend via Flask and JSON objects. JavaScript then uses the D3 library to convert the metric scores into a contour plot. The D3 library has many interactive capabilities, allowing the user to modify the evaluation to fit every requirement.

Committee
Dr. Rafal Angryk (chair)
Dr. Azim Ahmadzadeh