The Iterated Prisoner's Dilemma has been used for decades as a model of behavioral interactions. From the celebrated performance of Tit for Tat, to the introduction of the zero-determinant strategies, to the use of sophisticated structures such as neural networks, the literature has been exploring the performance of strategies in the game for years. Parts of my doctoral research focused on understanding strategies’ performance, and more specifically, the properties that make a strategy successful. I will be presenting results from various manuscripts where we used data-driven approaches to shed some light on strategies’ performance. Our data are collected using the Axelrod-Python library, a open source software, to simulate plays of the Iterated Prisoner’s Dilemma between strategies. Our approaches include analyzing a large scaled data analysis of computer tournaments, and training strategies to compete in round robin tournaments and Moran processes using reinforcement learning.