Search results

AbstractOpponents of the efficient markets hypothesis argue that predictability reflects the psychological factors and "fads" of irrational investors in a speculative market. In that, conventional time series analysis often fails to give an accurate forecast for financial processes due to inherent noise patterns, fat tails, and nonlinear components. A recent stream of literature on behavioral finance has revealed that boundedly rational agents using simple rules of thumb for their decisions under uncertainty provides a more realistic description of human behavior than perfect rationality with optimal decision rules. Consequently, the application of technical analysis in trading could produce high returns. Machine learning techniques have been employed in economic systems in modeling nonlinearities and simulating human behavior. In this study, we expand the literature that evaluates return sign forecasting ability by introducing a recurrent neural network approach that combines heuristic learning and short‐term memory emulation, thus mimicking the decision‐making process of boundedly rational agents. We investigate the relative direction‐of‐change predictability of the neural network structure implied by the Lee–White–Granger test as well as compare it to other well‐established models for the DJIA index. Moreover, we examine the relationship between stock return volatility and returns. Overall, the proposed model presents high profitability, in particular during "bear" market periods.

The present study builds upon the seminal work of Engel and West [2005, Journal of Political Economy 113, 485-517] and in particular on the relationship between exchange rates and fundamentals. The paper discusses the well-known puzzle that fundamental variables such as money supplies, interest rates, outputs etc. provide help in predicting changes in floating exchange rates. It also tests the theoretical result of Engel and West (2005) that in a rational expectations present-value model, the asset price manifests near–random walk behaviour if the fundamentals are I(1) and the factor for discounting future fundamentals is near one. The study explores the direction and nature of causal interdependencies and cross-correlations among the most widely traded currencies in the world, their country-specific fundamentals and their US-differentials. A new VAR/VECM-GARCH multivariate filtering approach is implemented, whilst linear and nonlinear non-causality is tested on the time series. In addition to pairwise causality testing, several different groupings of variables are explored. The methodology is extensively tested and validated on simulated and empirical data. The implication is that although exchange rates and fundamentals appear to be linked in a way that is broadly consistent with asset-pricing models, there is no indication of a prevailing causal behaviour from fundamentals to exchange rates or vice-versa. When nonlinear effects are accounted for, the evidence implies that the pattern of leads and lags changes over time. These results may influence the greater predictability of currency markets. Overall, fundamentals may be important determinants of FX rates, however there may be some other unobservable variables driving the currency rates that current asset-pricing models have not yet captured.