# calm down even if you got negative score. Let's shares your thoughts on this task

The market is almost always unpredictable, even very good model can not guarantee stable performance, since the pattern shown in the history may change in the future. I tested my models using 2*3months and got about roughly 0.05 on each(no leakage), but I got -0.0025 on the first update(the submitted model used all data). I feel so sad as many of you, but I think it is normal and I really enjoyed the competition.
I think the useful things for us would be sharing our thoughts this task, and learning from each other. Let me share my idea first.
We are asked to predict r15-beta*m15, where beta is the slope of linear fitting of passed return, so if you think linear relation exist, the expected target should be the fitting intercept(very close to zero). So we are actually asked to predict the unexpected extra return of each asset based on passed linear fitting.
Beta would be a feature that directly affect target. The beta is set to 'zero' if there is missing value in 3750 window, and we are actually asked to  predict r15. So I have two types of models, one for zero beta(predic r15) and the other for non-zero beta(predict r15-betam15).
Other features I used are [asset return, portfolio return, asset return-portfolio return, asset return for moving average] in passed [1,2,3,5,10,15,20,30,40,50,60] minute.
I used 12*5 LGBM models ensemble for this competition, every time I added Gaussian noise to all features and target.