Predicting Assignment Submissions in a Multiclass Classification Problem
Journal Title: TEM JOURNAL - Year 2015, Vol 4, Issue 3
Abstract
Predicting student failure is an important task that can empower educators to counteract the factors that affect student performance. In this paper, a part of the bigger problem of predicting student failure is addressed: predicting the students that do not complete their assignment tasks. For solving this problem, real data collected by our university’s educational platform was used. Because the problem consisted of predicting one of three possible classes (multi-class classification), the appropriate algorithms and methods were selected. Several experiments were carried out to find the best approach for this prediction problem and the used data set. An approach of time segmentation is proposed in order to facilitate the prediction from early on. Methods that address the problems of high dimensionality and imbalanced data were also evaluated. The outcome of each approach is shown and compared in order to select the best performing classification algorithm for the problem at hand.
Authors and Affiliations
Bogdan Drăgulescu, Marian Bucos, Radu Vasiu
Keywords
Related Articles
- EP ID EP163823
- DOI -
- Views 174
- Downloads 0
Technical Analysis of MOOCs
Lately, the globalization and massification of higher education offer involved more and more e-learning techniques inside universities. The article brings a perspective on our analyses of different trends in online...
Calibration and Validation of the VISSIM Parameters - State of the Art
As a stochastic, microscopic, time-step, behavior-based model with capabilities to provide application of programming interface (API) and simulation, VISSIM has become one of the most useful and reliable programs u...
Experiment is the Central Part of the Topic and Realized by IBSE Method
This paper presents a pedagogical experiment wichh was conducted in three departments socio-linguistic direction in which experiment is the central part of the topic and realized by IBSE (InguryBased Science Educ...
Determining Optimal Hourly and Annual Coefficient District Cooling - One of the Aspects use of Green Technology
Work together more cooling source (refrigeration machines) the system of centralized supply cooling energy ( SCSCE ) is a way to achieve cost-effective operation and safe and rational supply consumption area with c...
Possibility to Increase Biofuels Energy Efficiency used for Compression Ignition Engines Fueling
The paper presents the possibilities of optimizing the use of biofuels in terms of energy efficiency in compression ignition (CI) engines fueling. Based on the experimental results was determinate the law of variat...