Crude Oil Futures Price Prediction Based on CNN-LSTM incorporating News Headlines Feature Extraction
Abstract
and a combined model of convolutional neural networks and long and short-term memory for feature mining for sentiment analysis. Based
on the dual significance of reality and statistics, this paper takes the logarithmic return of crude oil futures settlement price as the prediction
target, and uses news headlines to identify the intrinsic influences affecting crude oil futures prices using topic modeling and sentiment anal_x005fysis. In this study, by selecting market data and text data of WTI crude oil futures from 2011 to 2022 for empirical analysis, the CNN-LSTM
prediction model is significantly better than other models.
Keywords
Full Text:
PDFReferences
[1] Kilian L. Not all oil price shocks are alike: Disentangling demand and supply shocks in the crude oil market [J]. American Eco_x005fnomic Review, 2009, 99(3): 1053-69.
[2] Pejić Bach M, Krstić Ž, Seljan S, et al. Text mining for big data analysis in financial sector: A literature review [J]. Sustainability,
2019, 11(5): 1277.
[3] Tissaoui K, Zaghdoudi T, Hakimi A, et al. Do Gas Price and Uncertainty Indices Forecast Crude Oil Prices? Fresh Evidence
Through XGBoost Modeling [J]. Computational Economics, 2022: 1-25.
[4] Araci D. Finbert: Financial sentiment analysis with pre-trained language models [J]. arXiv preprint arXiv:190810063, 2019.
[5] Siami-Namini S, Tavakoli N, Namin AS. A comparative analysis of forecasting financial time series using arima, lstm, and bilstm [J].
arXiv preprint arXiv:191109512, 2019.
[6] He Z, Zhou J, Dai HN, et al. Gold price forecast based on LSTM-CNN model; proceedings of the 2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing,
Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech), F, 2019 [C]. IEEE.
[7] Li J, Li G, Liu M, et al. A novel text-based framework for forecasting agricultural futures using massive online news headlines, [F].
[8] Li X, Shang W, Wang S. Text-based crude oil price forecasting: A deep learning approach, [F].
[9] Zhang Z, He M, Zhang Y, et al. Geopolitical risk trends and crude oil price predictability, [F].
DOI: http://dx.doi.org/10.18686/fm.v8i6.11724
Refbacks
- There are currently no refbacks.
