Meta Learning Strategies for Comparative and Efficient Adaptation to Financial Datasets
This research proposes a Meta learning framework for financial time series forecasting, designed to rapidly adapt to novel market conditions with minimal retraining. The framework operates in two stages: 1) pretraining on a diverse set of financial datasets, including stocks (e.g., MSFT, AAPL) and c...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10795129/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823859638807822336 |
|---|---|
| author | Kubra Noor Ubaida Fatima |
| author_facet | Kubra Noor Ubaida Fatima |
| author_sort | Kubra Noor |
| collection | DOAJ |
| description | This research proposes a Meta learning framework for financial time series forecasting, designed to rapidly adapt to novel market conditions with minimal retraining. The framework operates in two stages: 1) pretraining on a diverse set of financial datasets, including stocks (e.g., MSFT, AAPL) and cryptocurrencies (e.g., BTC, ETH), and 2) fine-tuning on recent data to adapt to new markets. The model utilizes XGBoost with dynamic feature engineering, which adjusts technical indicators (e.g., Relative Strength Index, Bollinger Bands) to account for evolving market conditions. Experimental results demonstrate that the proposed framework achieves significant improvements in Root Mean Squared Error (15%) and Mean Absolute Percentage Error (10%) compared to traditional methods, such as simple moving averages and exponential smoothing. These findings highlight the framework’s robustness, scalability, and ability to manage dynamic market behaviors, making it an effective tool for both short-term traders and long-term investors. Compared to LSTM-GARCH, the proposed Meta learning model achieves an RMSE of 0.82 (versus up to 10.11), an MAE of 0.61 (versus up to 8.39), and a DA of 67.33% (versus up to 50.44%). |
| format | Article |
| id | doaj-art-bc59e6f80d0b47268029a9e7f45cb179 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-bc59e6f80d0b47268029a9e7f45cb1792025-02-11T00:01:15ZengIEEEIEEE Access2169-35362025-01-0113241582417010.1109/ACCESS.2024.351649010795129Meta Learning Strategies for Comparative and Efficient Adaptation to Financial DatasetsKubra Noor0https://orcid.org/0009-0007-4545-4267Ubaida Fatima1https://orcid.org/0000-0003-0372-0858Department of Mathematics, NED University of Engineering and Technology, Karachi, PakistanDepartment of Mathematics, NED University of Engineering and Technology, Karachi, PakistanThis research proposes a Meta learning framework for financial time series forecasting, designed to rapidly adapt to novel market conditions with minimal retraining. The framework operates in two stages: 1) pretraining on a diverse set of financial datasets, including stocks (e.g., MSFT, AAPL) and cryptocurrencies (e.g., BTC, ETH), and 2) fine-tuning on recent data to adapt to new markets. The model utilizes XGBoost with dynamic feature engineering, which adjusts technical indicators (e.g., Relative Strength Index, Bollinger Bands) to account for evolving market conditions. Experimental results demonstrate that the proposed framework achieves significant improvements in Root Mean Squared Error (15%) and Mean Absolute Percentage Error (10%) compared to traditional methods, such as simple moving averages and exponential smoothing. These findings highlight the framework’s robustness, scalability, and ability to manage dynamic market behaviors, making it an effective tool for both short-term traders and long-term investors. Compared to LSTM-GARCH, the proposed Meta learning model achieves an RMSE of 0.82 (versus up to 10.11), an MAE of 0.61 (versus up to 8.39), and a DA of 67.33% (versus up to 50.44%).https://ieeexplore.ieee.org/document/10795129/Meta-learning techniquesfinancial market predictiongradient boosting algorithmsadvanced feature selectiondynamic predictive modelsmachine learning in finance |
| spellingShingle | Kubra Noor Ubaida Fatima Meta Learning Strategies for Comparative and Efficient Adaptation to Financial Datasets IEEE Access Meta-learning techniques financial market prediction gradient boosting algorithms advanced feature selection dynamic predictive models machine learning in finance |
| title | Meta Learning Strategies for Comparative and Efficient Adaptation to Financial Datasets |
| title_full | Meta Learning Strategies for Comparative and Efficient Adaptation to Financial Datasets |
| title_fullStr | Meta Learning Strategies for Comparative and Efficient Adaptation to Financial Datasets |
| title_full_unstemmed | Meta Learning Strategies for Comparative and Efficient Adaptation to Financial Datasets |
| title_short | Meta Learning Strategies for Comparative and Efficient Adaptation to Financial Datasets |
| title_sort | meta learning strategies for comparative and efficient adaptation to financial datasets |
| topic | Meta-learning techniques financial market prediction gradient boosting algorithms advanced feature selection dynamic predictive models machine learning in finance |
| url | https://ieeexplore.ieee.org/document/10795129/ |
| work_keys_str_mv | AT kubranoor metalearningstrategiesforcomparativeandefficientadaptationtofinancialdatasets AT ubaidafatima metalearningstrategiesforcomparativeandefficientadaptationtofinancialdatasets |