Qlib is an AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas to implementing productions. Qlib supports diverse machine learning modeling paradigms. including supervised learning, market dynamics modeling, and RL.
The data_handler_config define label as : ["Ref($close, -2) / Ref($close, -1) - 1"] . However the model objective is binary:
model: class: "HFLGBModel" module_path: "qlib.contrib.model.highfreq_gdbt_model" kwargs: objective: 'binary'
I think either change the label as 0/1 or change model objective as 'l2' might be reasonable.