Scribd
Upload
476 views2 pages

A Machine Learning Approach For Tracking and Predicting Student Performance in Degree Programs

This document proposes a machine learning approach for predicting student performance in degree programs. It discusses challenges in predicting student performance over time as students progress differently. The proposed approach uses a bi-layered model with base predictors and ensemble predictors to make predictions based on a student's evolving performance. It also uses latent factor models to discover course relevance for building efficient base predictors. An evaluation on a UCLA student dataset over three years shows this approach achieves better performance than benchmark methods.

Uploaded by

sireesha payyavula
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
476 views2 pages

A Machine Learning Approach For Tracking and Predicting Student Performance in Degree Programs

This document proposes a machine learning approach for predicting student performance in degree programs. It discusses challenges in predicting student performance over time as students progress differently. The proposed approach uses a bi-layered model with base predictors and ensemble predictors to make predictions based on a student's evolving performance. It also uses latent factor models to discover course relevance for building efficient base predictors. An evaluation on a UCLA student dataset over three years shows this approach achieves better performance than benchmark methods.

Uploaded by

sireesha payyavula
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Machine Learning Approach for Tracking and Predicting

Student Performance in Degree Programs

ABSTRACT:
Accurately predicting students’ future performance based on their ongoing academic
records is crucial for effectively carrying out necessary pedagogical interventions to ensure
students’ on-time and satisfactory graduation. Although there is a rich literature on predicting
student performance when solving problems or studying for courses using data-driven
approaches, predicting student performance in completing degrees (e.g. college programs) is
much less studied and faces new challenges: (1) Students differ tremendously in terms of
backgrounds and selected courses; (2) Courses are not equally informative for making
accurate predictions; (3) Students’ evolving progress needs to be incorporated into the
prediction. In this project, we develop a novel machine learning method for predicting
student performance in degree programs that is able to address these key challenges. The
proposed method has two major features. First, a bi-layered structure comprising of multiple
base predictors and a cascade of ensemble predictors is developed for making predictions
based on students’ evolving performance states. Second, a data-driven approach based on
latent factor models and probabilistic matrix factorization is proposed to discover course
relevance, which is important for constructing efficient base predictors. Through extensive
simulations on an undergraduate student dataset collected over three years at UCLA, we
show that the proposed method achieves superior performance to benchmark approaches.

EXISTING SYSYEM:
Many machine learning techniques, such as decision trees,
artificial neural networks, matrix factorization, collaborative filters and probabilistic
graphical models, have been applied to develop prediction algorithms. Most of this work
ignores the temporal/sequential effect that students improve their knowledge over time and
treats the prediction as a one-time task. To take the temporal/sequential effect into account, a
three-mode tensor factorization (on student/problem/time) technique was developed for
predicting student performance in solving problems in (Intelligent Tutoring Systems) ITSs
and a similarity-based algorithm was proposed to issue predictions of student grades in
courses only when a certain confidence level is reached. However, due to the above-
mentioned important differences of predicting student performance in degree programs, these
methods are not applicable in our setting.

DISADVANTAGES:
 Accuracy is Low.
 develop a collaborative filtering algorithm,
PROPSED SYSTEM:
In this paper, we propose a novel method for designing predictors based on the
evolving progress of students. Our approach to enable such progressive predictions is based
on the ensemble learning technique and integrates offline learning and online learning. The
proposed architecture consists of two layers — a base prediction layer and an ensemble
prediction layer.
In the base prediction layer, we construct a set of base predictors, implemented using
different prediction algorithms. For each base predictor the prediction result for student is
given the student’s static feature and the current performance state. The base predictors are
trained using a dataset consisting of all student data in the department without differentiating
areas to maximally utilize the data. In fact, predictor may even be trained differently for each
prediction task.
In the ensemble prediction layer, we construct an ensemble predictor for each term.
The ensemble predictor synthesizes the previous ensemble output and output of the base
predictors and makes a final prediction. The ensemble predictor is learned using student data
in the same area since students having different areas take different courses and in different
sequences and hence, the temporal correlation is likely to be different.

ADVANTAGES:
 Accuracy is Very high.
 we do not develop collaborative filtering prediction algorithms, although they can be
adopted as base predictors in our method
 we are using SVM, LR, RF, ENSEMBLE based prediction algorithms.

System Specification:
Software Requirements:
• Operating System: Windows
• Coding Language: Python

Hardware Requirements:
• Processor – i3
• Speed – 2.4 GHz
• RAM – 4 GB
• Hard Disk - 500 GB

You might also like