Pre-Finetuning with Impact Duration Awareness for Stock Movement Prediction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912047105572864 |
|---|---|
| author | Chiu, Chr-Jr Chen, Chung-Chi Huang, Hen-Hsen Chen, Hsin-Hsi |
| author_facet | Chiu, Chr-Jr Chen, Chung-Chi Huang, Hen-Hsen Chen, Hsin-Hsi |
| contents | Understanding the duration of news events' impact on the stock market is crucial for effective time-series forecasting, yet this facet is largely overlooked in current research. This paper addresses this research gap by introducing a novel dataset, the Impact Duration Estimation Dataset (IDED), specifically designed to estimate impact duration based on investor opinions. Our research establishes that pre-finetuning language models with IDED can enhance performance in text-based stock movement predictions. In addition, we juxtapose our proposed pre-finetuning task with sentiment analysis pre-finetuning, further affirming the significance of learning impact duration. Our findings highlight the promise of this novel research direction in stock movement prediction, offering a new avenue for financial forecasting. We also provide the IDED and pre-finetuned language models under the CC BY-NC-SA 4.0 license for academic use, fostering further exploration in this field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17419 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Pre-Finetuning with Impact Duration Awareness for Stock Movement Prediction Chiu, Chr-Jr Chen, Chung-Chi Huang, Hen-Hsen Chen, Hsin-Hsi Computation and Language Understanding the duration of news events' impact on the stock market is crucial for effective time-series forecasting, yet this facet is largely overlooked in current research. This paper addresses this research gap by introducing a novel dataset, the Impact Duration Estimation Dataset (IDED), specifically designed to estimate impact duration based on investor opinions. Our research establishes that pre-finetuning language models with IDED can enhance performance in text-based stock movement predictions. In addition, we juxtapose our proposed pre-finetuning task with sentiment analysis pre-finetuning, further affirming the significance of learning impact duration. Our findings highlight the promise of this novel research direction in stock movement prediction, offering a new avenue for financial forecasting. We also provide the IDED and pre-finetuned language models under the CC BY-NC-SA 4.0 license for academic use, fostering further exploration in this field. |
| title | Pre-Finetuning with Impact Duration Awareness for Stock Movement Prediction |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2409.17419 |