Why Machine Learning Is a Hot Button Issue for Quants

The information ratios nearly doubled from the factor approach and the machine learning approach was walk forward out of sample, while the factor approach had unavoidable in sample bis. When you choose the factor approach over the optimized machine learning approach, you're basically giving up high risk, agested returns for ease of explanation - which is sometimes a mutually beneficial trait. Highacter predicts higher stock returns are related to the underlying characteristic, not the auto correlation. It matters that the highest re-weigh has an effect on expected returns. A feature should drive more expected returns if it is dispersed as it is in linearage. And i should say, there is still an advantage to smart bata, which is easy transparency