Machine Learning Task for Stock Price Prediction
Budget: $50 – $60 USD
Only dedicated and expert candidates should bid on the same, task required to be delivered in 1 Day.!!
Objective: Predict future values of stock's adjusted close price and volume using historical data.
Data Description: You will be provided with a dataset for a single stock company covering the last four years. The dataset includes the following fields:
Date
Stock Open
Stock Low
Stock High
Stock Close
Stock Adjusted Close (Adj. Close)
Volume
Tasks:
Data Visualization:
Generate a line graph to show the trend of the stock's adjusted close price (Adj. Close) over time. Use the 'Date' field as the x-axis and 'Adj. Close' as the y-axis. This will help visualize how the stock prices have changed over the specified period.
Predictive Modeling:
Build a predictive model to forecast the future values of the adjusted close price and volume of the stock.
Explain your choice of model and any features you engineered.
Validate the model’s performance using appropriate metrics (e.g., RMSE, MAE) and discuss the results.
Include steps taken to avoid overfitting, such as regularization techniques, cross-validation, or using a validation set.
Model Visualization:
Provide a comparative visualization that includes the training data, actual test data, and predicted values on the same chart. This should ideally be done for both the adjusted close price and volume predictions.
Use different markers or colors to distinguish between actual and predicted values.
Requirements:
Programming Language: Python
Allowed Libraries: Any (e.g., pandas, numpy, matplotlib, scikit-learn, TensorFlow, PyTorch)
Submission: Include a detailed write-up of your findings, the complete source code, and relevant visualizations. Your write-up should explain the reasoning behind your methodology, feature selection, model choice, and interpretation of the results.
Acceptnce Criteria:
Accuracy of Predictions: How close are the predicted values to the actual values?
Model Robustness: How well does the model perform on unseen data?
Quality of Visualizations: Clarity and effectiveness of visual representations.
Code Quality: Cleanliness, readability, and efficiency of the Python code.
Justify decisions and interpret results.
Objective: Predict future values of stock's adjusted close price and volume using historical data.
Data Description: You will be provided with a dataset for a single stock company covering the last four years. The dataset includes the following fields:
Date
Stock Open
Stock Low
Stock High
Stock Close
Stock Adjusted Close (Adj. Close)
Volume
Tasks:
Data Visualization:
Generate a line graph to show the trend of the stock's adjusted close price (Adj. Close) over time. Use the 'Date' field as the x-axis and 'Adj. Close' as the y-axis. This will help visualize how the stock prices have changed over the specified period.
Predictive Modeling:
Build a predictive model to forecast the future values of the adjusted close price and volume of the stock.
Explain your choice of model and any features you engineered.
Validate the model’s performance using appropriate metrics (e.g., RMSE, MAE) and discuss the results.
Include steps taken to avoid overfitting, such as regularization techniques, cross-validation, or using a validation set.
Model Visualization:
Provide a comparative visualization that includes the training data, actual test data, and predicted values on the same chart. This should ideally be done for both the adjusted close price and volume predictions.
Use different markers or colors to distinguish between actual and predicted values.
Requirements:
Programming Language: Python
Allowed Libraries: Any (e.g., pandas, numpy, matplotlib, scikit-learn, TensorFlow, PyTorch)
Submission: Include a detailed write-up of your findings, the complete source code, and relevant visualizations. Your write-up should explain the reasoning behind your methodology, feature selection, model choice, and interpretation of the results.
Acceptnce Criteria:
Accuracy of Predictions: How close are the predicted values to the actual values?
Model Robustness: How well does the model perform on unseen data?
Quality of Visualizations: Clarity and effectiveness of visual representations.
Code Quality: Cleanliness, readability, and efficiency of the Python code.
Justify decisions and interpret results.