Effective Convergence Trading of Sparse, Mean Reverting Portfolios

This paper introduces an effective convergence trading algorithm for mean reverting portfolios using Long Short Term Memory (LSTM) neural networks. Utilizing known techniques for selection of sparse, mean reverting portfolios from asset dynamics following the VAR(1) model, we introduce a 2-step technique to effectively trade the optimal portfolio. Sequence-to-sequence (Seq2Seq) LSTM architecture is implemented to make longer term prediction of future portfolio values and establish a trading range. In addition, a simple LSTM network is applied to predict very precisely one time step ahead. Combining these two constructions, a sophisticated convergence trading algorithm is implemented which produced Sharpe ratios around 1.0 on optimal portfolios selected from historical \( S[NONSPACE] \& P500\) $S[NONSPACE]\&P500$ stocks during \(2015-2022\) $2015-2022$ . This represents a very significant improvement compared to the previous convergence trading algorithms on the same set of portfolios by around \(141\%\) $141\%$ on average.