SIG-FIN-017-03 のバックアップ(No.2)


第17回研究会

Artificial Intelligence Predictor for Multivariate Time Series with Deep-learning and Wavelet Analysis

著者

Takashi Shiono (Credit Suisse)

概要

The author integrated 1) multivariate time-series analysis, 2) deep-learning, and 3) wavelet transform technics to forecast financial and economic time-series data. More specifically, the general-purpose predictor was developed, which exploits large number of observable variables by summarizing them into latent factors through deep-learning. This can be regarded as a deep-learning version of Factor Augmented Vector Auto Regression model (FAVAR). As a preprocessing step, all observable variables are decomposed into cyclical components (waves) and a trend component by multiple resolution analysis based on wavelet transforms. FAVAR models are fitted to decompose series with extrapolating forecasts, and then integrated to build the fitted values and forecasts of the original series. The back-test for the period from Jan 2015 to Apr 2016 showed good performances of the 1-month- and 3-month-ahead forecasts for TOPIX, USDJPY and other economic indicators, comparted with the simple VAR model.

キーワード

Deep Learning, RNN, LSTM, VAR, FAVAR, Wavelet, Multi Resolution Analysis, Time Series, Forecast

論文

(10月5日以降に公表いたします。)

トップ   新規 一覧 単語検索 最終更新   ヘルプ   最終更新のRSS