Enhancing Lead Scoring and Prioritization in Ed-Tech companies Using Supervised Machine Learning

Mandal, Sumit Jeevan (2025) Enhancing Lead Scoring and Prioritization in Ed-Tech companies Using Supervised Machine Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (897kB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

The swift growth of online education brings about a very practical problem: sorting out the high-probability learners from the huge amounts of raw leads. The present research provides a leakage-conscious supervised machine learning pipeline that facilitates lead scoring automation based on a real world Ed-Tech dataset consisting of 9,240 leads. As many as nine post contact features were found out and excluded in order to make sure that the predictions function only on pre contact data. After applying stratified 80/20 train/test splitting and 5-fold cross-validation within the training partition, seven modeling approaches (Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, XGBoost, LightGBM and a Stacking Ensemble) were evaluated against one another. A tuned Random Forest yielded the highest performance on held-out data (test accuracy 79.76%, ROC-AUC = 0.861) and, after threshold calibration (optimal threshold 0.530), gave rise to balanced precision and recall. A very significant point is that the model discovered a "Hot" lead segment (28.0% of leads) with a 92.47% conversion rate which is a 2.40× increase over the 38.54% baseline and thus it has great operational value for sales prioritization. The resultant output is a serialized, deployment-ready preprocessing + model pipeline but operational integration, temporal validation, monitoring, and fairness audits are necessary before the system can be rolled out to enterprises for production use.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Del Rosal, Victor UNSPECIFIED
Uncontrolled Keywords:	Lead Scoring; Lead Prioritization; Machine Learning; Ed-Tech; Online Education Enrollment
Subjects:	L Education > L Education (General) L Education > LC Special aspects / Types of education > E-Learning Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Artificial Intelligence for Business
Depositing User:	Ciara O'Brien
Date Deposited:	03 Sep 2026 08:33
Last Modified:	03 Sep 2026 08:33
URI:	https://norma.ncirl.ie/id/eprint/9780

Actions (login required)

View Item