Measuring Financial Time Series Similarity - ICCBR 2021

Here we propose a novel similarity metric for financial time series that captures both deviations and trends. We also explain some problems associated with traditional Pearson correlation when applied in the financial context.

The content relates to the paper titled "Measuring Financial Time Series Similarity with a View to Identifying Profitable Stock Market Opportunities" that was presented at the International Conference for Case-Based Reasoning.

[chrisf]

This was really interesting, thanks ! I recently stumbled across the same issue, and I started wondering whether it was valid to just ignore the "subtract the mean return" step. Your presentation makes it much clearer, thanks. I really like the distinction between correlation of price and correlation of returns, that made everything much clearer. Thanks again :)

[axe]

DTW on cumulative returns are better. Also i would suppose a similarity in causal structure would be more rigourous for OOD generalizability

[vinayakmikkal]

Shouldn't the Pearson correlation be calculated on a sequential data? Order does matter.