Convolutional neural networks for financial text regression


Creative Commons License

Dereli N., SARAÇLAR M.

57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 - Student Research Workshop, SRW 2019, Florence, İtalya, 28 Temmuz - 02 Ağustos 2019, ss.331-337, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.18653/v1/p19-2046
  • Basıldığı Şehir: Florence
  • Basıldığı Ülke: İtalya
  • Sayfa Sayıları: ss.331-337
  • Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
  • Boğaziçi Üniversitesi Adresli: Evet

Özet

Forecasting financial volatility of a publiclytraded company from its annual reports has been previously defined as a text regression problem. Recent studies use a manually labeled lexicon to filter the annual reports by keeping sentiment words only. In order to remove the lexicon dependency without decreasing the performance, we replace bag-of-words model word features by word embedding vectors. Using word vectors increases the number of parameters. Considering the increase in number of parameters and excessive lengths of annual reports, a convolutional neural network model is proposed and transfer learning is applied. Experimental results show that the convolutional neural network model provides more accurate volatility predictions than lexicon based models.