基于 Python 的 AI 学生追踪系统：预测学业风险并支持早期干预

1. Project Information

• Module: Business Analysis 3.2
• Theme: AI Solution for Industries
• Project Title: AI Student Tracking System

2. Project Overview

The AI Student Tracking System is an Artificial Intelligence solution designed for the higher education environment. The system aims to identify students who may be at risk of poor academic performance or withdrawal at an early stage, allowing appropriate support and intervention to be provided. The solution uses Python and Artificial Intelligence techniques to analyse student-related data, identify patterns, predict academic risk, and provide useful information to support decision-making.

3. Problem Statement

Higher education institutions collect large amounts of student information, including academic performance, assessment results, attendance, and other relevant student data. However, identifying students who may be experiencing academic difficulties early enough can be challenging when this information is analysed manually or across separate systems. This project addresses the problem by developing an AI-based system that can analyse student data and identify students who may require additional academic support.

4. Proposed Solution

The system will analyse relevant student data and generate an indication of the student's academic risk level.

Features include:

• Student data preprocessing and cleaning
• Exploratory Data Analysis (EDA)
• Machine Learning for student risk prediction
• Time Series Analysis to monitor changes
• Deep Learning for complex patterns
• NLP for student interaction
• AI-powered chatbot
• Dashboard for predictions and insights

The system is intended to act as a decision-support tool and not as a replacement for lecturers or advisors.

5. Business Objectives

The main objectives of the project are to:

• Identify students who may be at risk at an early stage.
• Support data-driven decision-making within the education environment.
• Help academic staff prioritise students who may require intervention.
• Monitor student performance and identify changes over time.
• Support targeted academic interventions.
• Improve the efficiency of student-support processes.
• Contribute to improved student progression and retention.

6. AI Techniques

• Machine Learning :Classification algorithms will be used to analyse student information and predict whether a student may be at risk.
• Time Series Analysis :Student performance data will be analysed over time to identify changes, trends, and patterns in academic performance.
• Deep Learning :Neural network techniques will be explored to determine whether complex patterns in student data can improve prediction performance.
• Natural Language Processing :NLP will be used to support natural-language interaction between students and the system.
• Chatbot :An AI-powered chatbot will provide students with information based on the system's available insights and support features.
• Data :The project will use relevant student-related datasets containing information that can be used to analyse academic performance and student success.