STGV-Similarity between trend generating vectors: A new sample weighting scheme for stock trend prediction using financial features of companies

The problem of effective stock trend prediction has aroused much attention these years for its profitability. The development of algorithmic trading drives explosive growth in fast and effective techniques for trend predictions and analysis in securities. However, little attention has been paid to sample weighting schemes in this field. In this article, we propose a new sample weighting scheme targeted for stock trend prediction based on financial features. Specifically, stock trends are supposed to be determined by hidden market states named as trend generating vectors. These vectors can be generated from companies’ financial features. The scheme considers similarities between trend generating vectors (STGVs) when assigning weights to samples from different periods to differentiate their prediction capabilities. Similarity scores calculated with a proper metric are adopted to measure similarity. We combine STGV with classification algorithms to make stock trend predictions. Extensive experiments are conducted to figure out the most suitable similarity metric used in STGV and demonstrate the superiority of STGV over other sample weighting schemes.