About this question
Hard · machine_learning · Quant Researcher interview question · information_theory, time_series, causality, statistics
Identifying non-linear causal relationships between assets is crucial for pairs trading, lead-lag analysis, and market microstructure. Transfer Entropy (TE) is a non-parametric measure based on information theory that quantifies directed, asymmetric information transfer between time series, capturing relationships that standard correlation misses. Task Implement a function solution that calculates the Transfer Entropy from a source time series prices_x to a target time series prices_y. The calc