Robust returns ranking prediction and portfolio optimization for M6

The M6 competition aims to address challenging problems in stock returns ranking prediction and portfolio optimization. To tackle the volatility and low signal-to-noise ratio in the stock market, our team designs the overall solution from the robustness perspective. Regarding returns ranking prediction, we present the MultiTask Deep Neural Network with Denoising Autoencoder Enhancement (MT-DNN-DAE), which incorporates the self-supervised learning of DAE and jointly optimizes the multi-task loss. We propose Robust Feature Selection (RFS) to identify features with a high signal-to-noise ratio for DAE’s representation learning. We construct a separate branch for important ID features to prevent information loss. Results show our solution can accurately predict returns ranking while maintaining generalization. On the task of portfolio optimization, a Differential Evolution algorithm is presented to optimize asset allocation and maximize returns under risk constraints, demonstrating improved performance over traditional techniques. These methods led to a 4th place global ranking in the M6 competition.