Overview / Usage

Project Overview ● Briefly describe the purpose and objectives of the Early Warning System (EWS).

b. Stakeholders ● Identify key stakeholders involved in the project, including data scientists, educators, administrators, and IT personnel.

Methodology / Approach

Feature Engineering a. Relevant Features ● Enumerate and explain the features selected for dropout prediction (attendance rate, academic performance, engagement score). b. Time-Series Features ● Describe how time-series features were created to capture trends over time.

Model Development a. Model Selection ● Explain the rationale behind choosing the specific classification model for dropout prediction. b. Data Splitting ● Describe how the dataset was divided into training and testing sets. c. Model Training ● Detail the process of training the model on the training set. d. Model Evaluation ● Present the metrics used to evaluate the model's performance on the testing set (accuracy, precision, recall, F1 score). e. Fine-Tuning ● Document the process of adjusting hyperparameters to optimize model performance.

Early Warning System Integration a. Thresholds ● Specify the chosen thresholds that trigger alerts for educators. b. Alert System ● Describe the development of the alert system and how it communicates with educators (email, SMS, platform integration).

Continuous Monitoring and Improvement a. Regular Updates ● Explain how the model is periodically updated with new data to enhance accuracy. b. Feedback Loop ● Detail the mechanism for collecting and incorporating feedback from educators to improve the model.

Technologies Used

Python,Scikit_learn,Machine Learning,Streamlit

Documents and Presentations

Other links

• Student-Dropout-Prediction (https://github.com/Idk507/Student-Dropout-Prediction/tree/master)