Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

S&P 500 forecasting with financial news sentiment using FinBERT-CNN-LSTM

Bulletin of Electrical Engineering and Informatics · Vol. 15 No. 5 (2026) · hlm. 4474–4486

DOI
10.11591/eei.v15i5.11750
ISSN
2089-3191, 2302-9285
Terbit
2026-10-01
Penerbit
Institute of Advanced Engineering and Science (IAES)
Bahasa
en
Lisensi
creativecommons.org/licenses/by-sa/4.0/

Abstrak

Accurate stock market forecasting remains challenging due to the nonlinear, noisy, and volatile nature of financial markets. Beyond historical prices, market movements are influenced by financial news and investor sentiment. This study proposes a hybrid financial bidirectional encoder representations from transformers with convolutional neural network and long short-term memory (FinBERT-CNN-LSTM) model for forecasting the Standard & Poor’s 500 (S&P 500) index by integrating financial news sentiment with historical market data. FinBERT generates daily aggregated sentiment scores, which are combined with market features and processed through a CNN-LSTM architecture. The CNN captures local patterns and short-term interactions, while the LSTM models temporal dependencies in financial time series. Experimental results show that the proposed model outperforms benchmark models, achieving a root mean square error (RMSE) of 0.0119, mean absolute error (MAE) of 0.0091, mean absolute percentage error (MAPE) of 2.10%, and directional accuracy (DA) of 63.4%. It also achieves a cumulative return of 15.8% and a Sharpe ratio of 1.35. Rolling-window validation and Diebold–Mariano (DM) testing further support the statistical significance of the improvements. These findings demonstrate the effectiveness of combining financial sentiment and deep learning (DL) for stock market forecasting.

Kata kunci

Jaringan kolaborasi para penulis

10 penulis · 17 tautan kepenulisan bersama · 3 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Université Ibn-Tofail
  • Université Sultan Moulay Slimane
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Abdelaali KemmouUniversité Ibn-Tofail2
Moulay Hafid AabidiUniversité Sultan Moulay Slimane2
Nawfal El MoukhiUniversité Ibn-Tofail1
Soufiane HajbiUniversité Ibn-Tofail1
Moulay Hicham HaninUniversité Ibn-Tofail1
Oussama SbaytiUniversité Ibn-Tofail1
Khalid HousniUniversité Ibn-Tofail1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S2765016208, pertama di-harvest 19 Nov 2026, terakhir terlihat 19 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">S&amp;P 500 forecasting with financial news sentiment using FinBERT-CNN-LSTM</dc:title><dc:creator>Zakaria Al Bakkari</dc:creator><dc:creator>Ikram El Azami</dc:creator><dc:creator>Adil El Makrani</dc:creator><dc:subject>stock market prediction</dc:subject><dc:subject>financial news sentiment</dc:subject><dc:subject>FinBERT</dc:subject><dc:subject>CNN-LSTM hybrid model</dc:subject><dc:subject>investor sentiment</dc:subject><dc:subject>financial time series</dc:subject><dc:subject>directional accuracy</dc:subject><dc:subject>Diebold-Mariano test</dc:subject><dc:description xml:lang="en">Accurate stock market forecasting remains challenging due to the nonlinear, noisy, and volatile nature of financial markets. Beyond historical prices, market movements are influenced by financial news and investor sentiment. This study proposes a hybrid financial bidirectional encoder representations from transformers with convolutional neural network and long short-term memory (FinBERT-CNN-LSTM) model for forecasting the Standard &amp; Poor’s 500 (S&amp;P 500) index by integrating financial news sentiment with historical market data. FinBERT generates daily aggregated sentiment scores, which are combined with market features and processed through a CNN-LSTM architecture. The CNN captures local patterns and short-term interactions, while the LSTM models temporal dependencies in financial time series. Experimental results show that the proposed model outperforms benchmark models, achieving a root mean square error (RMSE) of 0.0119, mean absolute error (MAE) of 0.0091, mean absolute percentage error (MAPE) of 2.10%, and directional accuracy (DA) of 63.4%. It also achieves a cumulative return of 15.8% and a Sharpe ratio of 1.35. Rolling-window validation and Diebold–Mariano (DM) testing further support the statistical significance of the improvements. These findings demonstrate the effectiveness of combining financial sentiment and deep learning (DL) for stock market forecasting.</dc:description><dc:publisher>Institute of Advanced Engineering and Science (IAES)</dc:publisher><dc:date>2026-10-01</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.11591/eei.v15i5.11750</dc:identifier><dc:identifier>10.11591/eei.v15i5.11750</dc:identifier><dc:source>Bulletin of Electrical Engineering and Informatics; Vol 15 No 5 (2026); 4474-4486</dc:source><dc:source>2089-3191</dc:source><dc:source>2302-9285</dc:source><dc:language>en</dc:language><dc:relation>https://beei.org/index.php/EEI/article/download/11750/5025</dc:relation><dc:rights>https://creativecommons.org/licenses/by-sa/4.0/</dc:rights></oai_dc:dc>