023-04

| Topic path: Top / 023-04

[[第23回研究会>023]]

*DSGEによるニューラルネットの正則化と経済予想 [#i0c644ac]

**著者 [#j63171f4]
塩野剛志(クレディ・スイス証券)

**概要 [#jb33486e]
This paper examines the possibility of combining a DSGE model and neural networks to supplement each other, with regard to out-of-sample forecasts for economic variables. The aim is to build a model with theoretical interpretability and state-of-the-art performance. The novel neural-net structure of TDVAE (Temporal Difference Variational Auto-Encoder) proposed by Gregor et.al [2019] enables to realize this idea. TDVAE virtually replicates a Gaussian stochastic state-space model through combination of neural networks. Because a DSGE model provides theoretical restrictions on the state transition and observation matrices of a linear state-space model, I choose to transplant those DSGE-oriented matrices into the formulations of state transition and observation probabilities in TDVAE. This TDVAE-DSGE approach certainly achieved the superior performance in the task of out-of-sample forecasts on Japan's real GDP during 1Q/2011 and 4Q/2018. 

**キーワード [#yb8409c0]
Neural Network, DSGE, VAE, LSTM

**論文 [#y5a5534a]

(10月9日以降に公表いたします)
//&ref(SIG-FIN-023-04.pdf);
//&ref(04_SIG-FIN-23.pdf);
トップ   編集 差分 バックアップ 添付 複製 名前変更 リロード   新規 一覧 単語検索 最終更新   ヘルプ   最終更新のRSS