Forecasting the Market Returns And Portfolio Enhancement With Frequency-Decomposed Institutional Investor Sentiment: Evidence From the Taiwan Futures Market

Abstract

This study examines the predictive power of changes in institutional investor sentiment in the Taiwan futures market for forecasting stock index futures and aggregate stock market returns. Using wavelet decomposition, the results show that long-term sentiment changes outperform the buy-and-hold strategy, historical averages, undecomposed sentiment, and sentiment measures at other time scales in terms of predictive power and portfolio enhancement across the full sample. Additionally, a Markov-switching model is applied to identify bull and bear market regimes and then to assess portfolio enhancement performance within each regime. The empirical findings reveal that, in bull markets, the long-term sentiment-based strategy outperforms the benchmarks mentioned above. In bear markets, a medium-term sentiment-based strategy delivers significant improvements in portfolio enhancement performance compared to the same aforementioned benchmarks. These results deepen our understanding of how institutional investor sentiment influences asset returns and offer valuable insights for tailoring portfolio management.