Bridging the divide in financial market forecasting: machine learners vs. financial economists

Abstract

Abstract-Financial time series forecasting is a popular application of machine learning methods. Previous studies report that advanced forecasting methods predict price changes in financial markets with high accuracy and that profit can be made trading on these predictions.However, financial economists point to the informational efficiency of financial markets, which questions price predictability and opportunities for profitable trading. The objective of the paper is to resolve this contradiction. To this end, we undertake an extensive forecasting simulation, based on data from thirty-four financial indices over six years. These simulations confirm that the best machine learning methods produce more accurate forecasts than the best econometric methods. We also examine the methodological factors that impact the predictive accuracy of machine learning forecasting experiments. The results suggest that the predictability of a financial market and the feasibility of profitable model-based trading are significantly influenced by the maturity of the market, the forecasting method employed, the horizon for which it generates predictions and the methodology used to assess the model and simulate model-based trading. We also find evidence against the informational value of indicators from the field of technical analysis. Overall, we confirm that advanced forecasting methods can be used to predict price changes in some financial markets and we discuss whether these results question the prevailing view in the financial economics literature that financial markets are efficient.

Forex exchange rate forecasting using deep recurrent neural networks

“…Neural networks have been a popular instrument for financial forecasting for decades and represent the backbone of modern modeling approaches in the scope of deep learning. With regard to their applications in finance, feedforward neural networks (FNN) have received much recognition and have been used by several studies to predict price movements (Hsu et al 2016). From a methodological point of view, RNNs are better suited to process sequential data (i.e., temporal financial data) than other network architectures.…”

Comparative Analysis of Investment Decision Models

“…Nepaisant to, techniniai rodikliai plačiai naudojami įvairiose kompiuterinėse sistemose ir integruojami su kitais kintamaisiais, pavyzdžiui, kasdienės naujienos finansų rinkose ir pan. (Hsu et al 2016). 1 lentelėje galima matyti, kad analizuojami prognozavimo modeliai gali skirtis pagal savo rezultatą: prognozuojama kainos kitimo kryptis (kyla arba krinta), prognozuojamos tikslios akcijų kainos įvertina investavimo, atsižvelgiant į gautą prognozę, pelningumą.…”

“…Deja, jie neįtraukia naujausių akcijų kainų, kitaip nei dinamiški modeliai, kurie įvertina skirtingos kilmės ir periodų laiko eilutes, ir naudoja naujausius mokymosi šablonus. Be to, statiški modeliai gali pervertinti akcijų kainas, o dinamiški modeliai mažina tokių klaidų tikimybę (Hsu et al 2016).…”

“…Vieno sluoksnio neuronai yra visiškai prijungti prie kitų neuronų. Tokie modeliai gali geriau susidoroti su tolygiaisiais duomenimis (Lessmann et al 2011), kurie dažnai pasireiškia prognozuojant laiko eilutes (Hsu et al 2016). Guresen et al (2011) dirbtinio neuronų tinklo privalumais įvardija tai, kad jo nesudaro standartinės formulės ir jis gali lengvai prisitaikyti prie rinkos sąlygų.…”

“…Deja, jie neįtraukia naujausių akcijų kainų, kitaip nei dinamiški modeliai, kurie įvertina skirtingos kilmės ir periodų laiko eilutes, ir naudoja naujausius mokymosi šablonus. Be to, statiški modeliai gali pervertinti akcijų kainas, o dinamiški modeliai mažina tokių klaidų tikimybę (Hsu et al 2016).Prognozės tikslumas, be abejo, priklauso ne tik nuo modelio, bet ir nuo to, kaip ir kokie nepriklausomi kintamieji koreliuoja su tiksliniu kintamuoju. Per pastaruosius kelis dešimtmečius mokslininkai patobulino tradicinius skaitinius prognozavimo modelius (Cheng et al 2010).…”