103: Dave Bergstrom – Escaping Randomness, and Turning to Data for an Edge
Chat With Traders
00:00
How to Prevent Curve Fitting in Data Mining
A lot of people associate data mining with just optimization. Picking at patterns, for example, the high above the high of two ago is much better than just picking a moving average and finding the best length. Cross validation where you would basically slice the data into pieces and test on the different pieces. Some other ways are making sure you don't use parameters that lend themselves to optimization.
Transcript
Play full episode
