Paper: arXiv 2412.17314
Authors: Pengbin Feng, Yankaiqi Li, Yijiashun Qi, Xiaojun Guo, Zhenghao Lin
Abstract
This study proposes a multi-task learning framework based on ResNeXt, aiming to solve the problem of feature extraction and task collaborative optimization in financial data mining. Financial data usually has the complex characteristics of high dimensionality, nonlinearity, and time series, and is accompanied by potential correlations between multiple tasks, making it difficult for traditional methods to meet the needs of data mining. This study introduces the ResNeXt model into the multi-task learning framework and makes full use of its group convolution mechanism to achieve efficient extraction of local patterns and global features of financial data. At the same time, through the design of task sharing layers and dedicated layers, it is established between multiple related tasks. Deep collaborative optimization relationships. Through flexible multi-task loss weight design, the model can effectively balance the learning needs of different tasks and improve overall performance. Experiments are conducted on a real S&P 500 financial data set, verifying the significant advantages of the proposed framework in classification and regression tasks. The results indicate that, when compared to other conventional deep learning models, the proposed method delivers superior performance in terms of accuracy, F1 score, root mean square error, and other metrics, highlighting its outstanding effectiveness and robustness in handling complex financial data. This research provides an efficient and adaptable solution for financial data mining, and at the same time opens up a new research direction for the combination of multi-task learning and deep learning, which has important theoretical significance and practical application value.
Complexity vs Empirical Score
- Math Complexity: 7.0/10
- Empirical Rigor: 6.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper employs advanced deep learning concepts like ResNeXt and multi-task learning with specific architecture designs, indicating high math complexity, while providing empirical validation on real S&P 500 data with multiple performance metrics, showing solid but not exhaustive empirical rigor.
Research Flowchart
flowchart TD A["Research Goal:<br>Optimize Financial Data Mining<br>via Multi-Task Learning"] --> B["Dataset: S&P 500 Data<br>(High Dim, Nonlinear, Time Series)"] B --> C["Core Methodology:<br>ResNeXt-based<br>Multi-Task Framework"] C --> D["Model Architecture:<br>Group Convolutions<br>Task Sharing & Dedicated Layers"] D --> E["Computational Process:<br>Flexible Multi-Task Loss<br>Weight Design & Optimization"] E --> F["Key Findings:<br>Superior Classification & Regression<br>Metrics (Accuracy, F1, RMSE)"] F --> G["Outcome:<br>Robust Financial Mining Solution<br>Novel Deep Learning Direction"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes a multi-task learning framework based on ResNeXt for financial data mining.
Source sentence
This study proposes a multi-task learning framework based on ResNeXt, aiming to solve the problem of feature extraction and task collaborative optimization in financial data mining.
Assumes 1
- Financial data has high dimensionality, nonlinearity, and time series characteristics. data
Source sentence
Financial data usually has the complex characteristics of high dimensionality, nonlinearity, and time series, and is accompanied by potential correlations between multiple tasks
Data
- S&P 500 stock market dataset market-prices public
Source sentence
This study selected the S&P 500 stock market dataset as the data source for the experiment. This dataset is a widely used public dataset in the field of financial data mining, which contains historical trading data and market indicators of all constituent stocks in the S&P 500 index.
Costs
Not applicable
Finds 3
- The proposed ResNeXt-based multi-task learning framework outperforms other models in both classification and regression tasks. performance
Source sentence
The proposed ResNeXt-based multi-task learning framework outperforms other models in both classification and regression tasks.
- In classification, it achieved an accuracy of 85.3% and a macro F1 score of 83.7%, higher than the next best model. predictive-accuracy
Source sentence
In classification, it achieved an accuracy of 85.3% and a macro F1 score of 83.7%, significantly higher than the second-ranked multi-channel convolutional neural network (MCCNN).
- In regression, the mean absolute error was 0.025 and the root mean square error was 0.043, demonstrating excellent prediction capabilities. predictive-accuracy
Source sentence
In regression, the mean absolute error (MAE) was 0.025, and the root mean square error (RMSE) was 0.043, demonstrating excellent prediction capabilities.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 34 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.