Teaching Machine Learning Through Cricket: A Practical Engineering Education Approach

TL;DR

The paper tackles the gap between theoretical ML knowledge and practical engineering problem solving by introducing LearnML@Cricket, a 12-week, context-based curriculum that embeds ML concepts in cricket analytics. By mapping game scenarios to Markov Decision Processes, Bayesian uncertainty, and exploration-exploitation through multi-armed bandits, the approach provides concrete, data-rich experiences that align with Kolb's experiential learning and situated cognition theories. The authors detail the pedagogical framework, module structure, implementation examples, and a comprehensive empirical evaluation plan, including pre/post concept inventories, transfer tasks, and industry collaborations. If validated, this approach offers a replicable model for enhancing conceptual understanding and practical transfer of ML skills to engineering practice, with open-source materials to support broad adoption.

Abstract

Teaching complex machine learning concepts such as reinforcement learning and Markov Decision Processes remains challenging in engineering education. Students often struggle to connect abstract mathematics to real-world applications. We present LearnML@Cricket, a 12-week curriculum that uses cricket analytics to teach these concepts through practical, hands-on examples. By mapping game scenarios directly to ML algorithms, students learn through doing rather than memorizing. Our curriculum includes coding laboratories, real datasets, and immediate application to engineering problems. We propose an empirical study to measure whether this approach improves both understanding and practical implementation skills compared to traditional teaching methods.