Multi-step non- and semi-parametric predictive regressions for short and long horizon stock return prediction

Abstract

In this paper, we propose three new predictive models: the multi-step nonparametric predictive regression model and the multi-step additive predictive regression model, in which the predictive variables are locally stationary time series; and the multi-step time-varying coefficient predictive regression model, in which the predictive variables are stochastically nonstationary. We also establish the estimation theory and asymptotic properties for these models in the short horizon and long horizon case. To evaluate the effectiveness of these models, we investigate their capability of stock return prediction. The empirical resultsshow that all of these models can substantially outperform the traditional linear predictive regression model in terms of both in-sample and out-of-sample performance. In addition, we find that these models can always beat the historical mean model in terms of in-sample fitting, and also for some cases in terms of the out-of-sample forecasting.

Forecasting benchmarks of long-term stock returns via machine learning

“…Vogt (2012) states that his convergence result is not valid in a forecasting context. However, Cheng et al (2018) provide predictive models and estimation theory for the local-constant case and locally stationary regressors. They apply their methods to monthly stock market data and find improved predictability of their models compared to traditional linear predictive regression models.…”

Minimum Message Length in Hybrid ARMA and LSTM Model Forecasting

“…The stock return prediction is one of most popular research topic in financial application [27,31]. This section studies the performance of the hybrid model by MML87 The empirical results show that the hybrid model ARIMA-LSTM can substantially outperform the traditional time series ARIMA model, particularly in the size of forecast window T= 5, 30, 100, 130, 150, and 200.…”

“…This section studies the performance of the hybrid model by MML87 The empirical results show that the hybrid model ARIMA-LSTM can substantially outperform the traditional time series ARIMA model, particularly in the size of forecast window T= 5, 30, 100, 130, 150, and 200. Many studies demonstrated that the stock return depends on various factors such as dividend yield, the book to market ratio, and/or interest rate [27][28][29]. However, traditional linear time series models are difficult to consider the effect of all those factors, it requires a more complex model to capture the information hidden in residual from the ARIMA model.…”

Minimum Message Length in Hybrid ARMA and LSTM Model Forecasting

“…There are 10 different 173 parameter sets from p 1 , ..., p 5 and q 1 , ..., q 2 . The values in the table are the average of The stock return prediction is one of most popular research topic in financial 227 application [26,30]. This section studies the performance of the hybrid model by MML87,…”

“…5, 30, 100, 130, 150, and 200. Many studies demonstrated that the stock 238 return depends on various factors such as dividend yield, the book to market ratio, 239 and/or interest rate[26][27][28]. However, traditional linear time series models are difficult 240 to consider the effect of all those factors, it requires a more complex model to capture Mean, standard deviation, pacf lag 1 to 3 for ten selected stocks…”