Incorporation of Foreign Exchange Risk to Fama-French Factor Model: A Study on Borsa İstanbul

Höçük, Furkan
This empirical study compares the relative performances of the Fama-French five-factor model without foreign exchange risk and the five-factor model incorporating foreign exchange risk on capturing portfolio returns in Borsa İstanbul. The main contribution of our study to the asset pricing literature is the incorporation of FX risk to the Fama-French five-factor model. We propose an additional factor as a proxy for FX risk. Another contribution of this study is implementing a machine learning technique, support vector regression (SVR), to estimate portfolio returns through the FF5F model without FX risk and FF5F model incorporating FX risk for Borsa İstanbul stocks. Although there are numerous researches investigated on Borsa İstanbul, any other study did not implement SVR via CAPM or Fama French multi-factor models to the best of our knowledge. There are empirical studies that confirm the efficiency of SVR. Some studies also compare the performance of the linear factor regression method with alternative statistical tools, including machine learning methods. Our study stands out in combining predictions of simple linear regression and SVR methods. Optimal weights obtained from linear combinations imply more precise estimations through SVR. In 28 out of 36 combinations, we observed that optimal weights assigned to SVR estimations were greater than those assigned to SLR estimations. Linear regression methods may be too restrictive to reflect the non-linearity of factor exposures under the Fama-French multi-factor model scheme. Asset pricing models, which take nonlinear aspects of the stock markets into consideration, might generate more precise estimations.


Forecasting direction of exchange rate fluctuations with two dimensional patterns and currency strength
Özorhan, Mustafa Onur; Toroslu, İsmail Hakkı; Department of Computer Engineering (2017)
This thesis presents a method to predict the direction and magnitude of movement of currency pairs in the foreign exchange market. The method uses clustering and classification methods with a combination of two dimensional chart patterns, processed price data and technical indicator data. The input data is adapted to each trading day with a moving time-frame. The accuracy of the prediction models are tested across several different currency pairs. The experimental results suggest that using two dimensional ...
Aslan, Mustafa; Gaygısız Lajunen, Esma; Department of Financial Mathematics (2021-8-04)
This study examines the effects of the exchange rate volatility and the firm-specific features representing the liquidity, profitability, and leverage performance of firms on excess stock returns for the manufacturing firms listed in Borsa İstanbul (BIST) using dynamic panel data model. The exchange rate volatility is modeled by single regime generalized autoregressive conditional heteroscedasticity (GARCH) models and Markov-switching GARCH (MSGARCH) models. The MSGARCH models show evidence that the evoluti...
The role of foreign investors in the İstanbul Stock Exchange
Usta, Murat; Güner, Zehra Nuray; Department of Business Administration (2003)
This master thesis examines the role of foreign investors in the Istanbul Stock Exchange in three dimensions: differences among sectors and subsectors in terms of foreign trading activity, the effect of November 2000 ا February 2001 crisis on returns and foreign trading activity, and the relationship between return and foreign trading activity. Data used in this thesis covers 72 months between January 1997 and December 2002. Significant differences among sectors and subsectors in terms of foreign trading ac...
Türkiye döviz piyasalarında oynaklığın öngörülmesi ve risk yönetimi kapsamında değerlendirilmesi
Ülkem, Başdaş; Soytaş, Uğur (2010-01-01)
Bu çalışmada, Türkiye döviz piyasalarında TRL/USD, TRL/EUR ve TRL/GBP serilerinin oynaklığı hareketli ortalama modelleri, AR ve ARMA modelleri ve ARCH süreçleri kullanılarak modellenmiş ve modellerin örneklem dışı öngörü performansları karşılaştırılmıştır. Farklı oynaklık öngörüleri kullanılarak elde edilen parametrik VaR modelinin öngörü performansları Basle Komitesi geriye dönük test ölçütleri kapsamında değerlendirilmiştir. Son küresel finansal krizin risk ölçüm teknikleri üzerindeki etkileri ayrıca...
An Examination of betas for Borsa İstanbul
Koca, Onur; Oran, Adil; Department of Business Administration (2016)
This study aims to investigate the Betas, which is called as systematic risk and introduced by Capital Asset Pricing Model (CAPM), of stocks traded in Borsa Istanbul (BIST). Issues about Beta have been examined for many years and mainly focus on its estimation and stability. These topics set up the core of this thesis. The closing prices of 203 eligible stocks between 2005 and 2015 are used in the work and data is collected from Thomson Reuters. The estimation of Beta is performed in four different methods,...
Citation Formats
F. Höçük, “Incorporation of Foreign Exchange Risk to Fama-French Factor Model: A Study on Borsa İstanbul,” M.S. - Master of Science, Middle East Technical University, 2022.