환율과 기초여건 간 괴리에 대한 연구: 시장심리를 중심으로(Exchange Rate Predictability Based on Market Sentiments)

본 연구는 기존 정형화된 환율 예측모형과 더불어 외환시장의 시장심리지수가 환율예측에 도움이 되는지 점검해 보고자 한다. 그리고 시장심리지수를 사용하여 외환시장 딜러들이 사용하는 반대의견(contrarion opinion) 투자전략에 기반하여 환율을 예측해 보았다. 또한 경제여건변수 및 시장심리지수를 종합적으로 활용한 기계학습 모형이 환율 예측력을 높일 수 있는지도 살펴보았다. Central bankers, policymakers, and market participants need topredict the future exchange rate movement. However, awell-known puzzle is that exchange rates are difficult to forecastusing observable macro fundamental variables. Meese and Rogoff(1983) report that the random walk model is better at predictingexchange rates in out-of-sample forecasts than models reflectingchanges in economic fundamentals. A large body of literature hasfound that, in attempting to solve the Meese‐Rogoff puzzle, therandom walk beats fundamentals-based models for periods up to aone‐year forecasting horizon. This study intends to examine whether the market sentiment index of the foreign exchange market, along with the standardizedfundamental-based models, helps predict the exchange rate. Basedon the market sentiment index data, we try to predict the exchangerate based on the contrary opinion investment strategy used byforeign exchange market dealers. We also examine whether machine learning models incorporating a wide range of economic data and market sentiment indices can improve exchange rateforecasting. This study mainly consists of four parts. Chapter 2 re-examines whether fundamental-based models can have prediction power onexchange rates. We examine developing market currencies, including the Korean won, in addition to major currencies. TheTaylor-rule model has short-term predictability on the Canadiandollar, Swiss franc, and British pound among major currencies. Formost models we analyze, emerging market currencies tend to showhigher long-term and short-term predictability than majorcurrencies. However, there is a significant variation in the predictive power of fundamental models over currency and period. In Chapter 3, the market sentiment index and Bloomberg’s exchange rate forecast are tested in terms of their ability to predictexchange rates. To compare the exchange rate predictability fundamental-based models in Chapter 2, we make them in identicalconditions: the data is transformed to monthly, and a single linearequation model is used. Both the market sentiment index and theBloomberg exchange rate forecast demonstrate high short-termexchange rate predicting power against the Euro. However, theyhave lower exchange rate forecasting power to other major currencies than the random walk model. (the rest omitted)