search

karolinachalupova / DiplomaThesis

Explaining Equity Returns with Interpretable Machine Learning
1 stars 0 forks source link

Liquidity filter - do I have the right data from @martinhronec? #3

Closed karolinachalupova closed 3 years ago

karolinachalupova commented 4 years ago

@martinhronec Tomas mentioned that there was a problem with the liquidity filter. I do not have the code of your liquidity filter, just the dscodes that pass the filter. Tomas said that the filter was more strict than it should be. I just want to make sure I have the right data. Even if I dont, this may be immaterial, as the filter is not wrong, just strict.

martinhronec commented 4 years ago

@KarolinaChalupova, send me the name of the datafiles you have, please.

karolinachalupova commented 4 years ago

@martinhronec filenames: DST_returns.gzip, DST_signals.gzip, DST_universe_filter.gzip

martinhronec commented 4 years ago

@KarolinaChalupova Open it and check if there are US companies or not.

karolinachalupova commented 3 years ago

@martinhronec There are no US companies, just Europe, Asia and Japan. In DST_signals, there are 30,088 unique DTID. After applying the DST_universe_filter, this reduces to 8,350 unique DTID.

karolinachalupova commented 3 years ago

@martinhronec Also, could you please send me the code for the filter and data cleaning (to see how the DST_universe_filter is obtained)?

martinhronec commented 3 years ago

@KarolinaChalupova data cleaning and filtering code shared as well as WRDS_data files. There is a lot of going on in data-preprocessing, I would not dedicate too much time to it right now.