Saved in:
| Main Authors: | , |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.15829018 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866902069324021760 |
|---|---|
| author | Harshwardhan Chaudhari Komal Prajapati |
| author_facet | Harshwardhan Chaudhari Komal Prajapati |
| contents | <p>Stock price movement is highly non-linear and complex, making accurate prediction challenging. Traditional methods such as Linear Regression and Support Vector Regression have been used but with limited accuracy. Researchers have attempted to enhance stock price prediction using ARIMA, but the high volatility in stock prices has led to the adoption of deep learning techniques, which have demonstrated superior accuracy across various analytics fields. Artificial Neural Networks (ANN) were applied for stock price prediction, but due to the time-series nature of stock prices, Recurrent Neural Networks (RNN) were introduced to improve prediction accuracy. However, RNNs struggle with capturing long-term dependencies and suffer from vanishing gradient issues. To address these challenges, Long Short-Term Memory (LSTM) networks were employed, optimizing stock price prediction and forecasting. In addition, this research aims to develop a novel approach to portfolio optimization by integrating advanced machine learning models, specifically Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), with the Mean-Variance (MV) model, enhancing both stock price prediction and portfolio formation.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_15829018 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Hybrid Machine Learning Approaches for Optimizing Stock Price Prediction and Portfolio Management Harshwardhan Chaudhari Komal Prajapati <p>Stock price movement is highly non-linear and complex, making accurate prediction challenging. Traditional methods such as Linear Regression and Support Vector Regression have been used but with limited accuracy. Researchers have attempted to enhance stock price prediction using ARIMA, but the high volatility in stock prices has led to the adoption of deep learning techniques, which have demonstrated superior accuracy across various analytics fields. Artificial Neural Networks (ANN) were applied for stock price prediction, but due to the time-series nature of stock prices, Recurrent Neural Networks (RNN) were introduced to improve prediction accuracy. However, RNNs struggle with capturing long-term dependencies and suffer from vanishing gradient issues. To address these challenges, Long Short-Term Memory (LSTM) networks were employed, optimizing stock price prediction and forecasting. In addition, this research aims to develop a novel approach to portfolio optimization by integrating advanced machine learning models, specifically Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), with the Mean-Variance (MV) model, enhancing both stock price prediction and portfolio formation.</p> |
| title | Hybrid Machine Learning Approaches for Optimizing Stock Price Prediction and Portfolio Management |
| url | https://doi.org/10.5281/zenodo.15829018 |