Forecasting the Finnish house price returns and volatility: a comparison of time series models

Purpose The purpose of this paper is to compare different models’ performance in modelling and forecasting the Finnish house price returns volatility. Design/methodology/approach competing models are autoregressive moving average (ARMA) model fractional integrated (ARFIMA) for returns. For volatility, exponential generalized conditional heteroscedasticity (EGARCH) with GARCH (FIGARCH) component (CGARCH) models. Findings Results reveal that, returns, data set under study drives ARMA or ARFIMA model. EGARCH stands as leading volatility modelling. long memory (ARFIMA, CGARCH FIGARCH) provide superior out-of-sample forecasts volatility; they outperform their short counterparts most regions. Additionally, in-sample fit performances vary from region region, while some areas, manifest a geographical pattern performances. Research limitations/implications research results have vital implications, namely, portfolio allocation, investment risk assessment decision-making. Originality/value To best author’s knowledge, Finland, there has yet be empirical either or/and Therefore, aims bridge that gap by comparing modelling, well studied market.