MATHVISION PROTOTYPE USING PREDICTIVE ANALYTICS
Malaysia is currently going towards Industrial Revolution (IR) 4.0 which makes Science, Technology, Engineering and Mathematics (STEM) subjects become more crucial. IR 4.0 covers a lot of aspects especially in digital transformation in manufacturing, and this certainly requires strong mathematical k...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
UiTM Press
2023-10-01
|
| Series: | Malaysian Journal of Computing |
| Subjects: | |
| Online Access: | https://mjoc.uitm.edu.my/main/images/journal/vol8-2-2023/4_MATHVISION_PROTOTYPE_USING_PREDICTIVE_ANALYTICS.pdf |
| _version_ | 1827647679864242176 |
|---|---|
| author | Muhd Syahir Abdul Razak Shuzlina Abdul-Rahman Mastura Hanafiah Amien Ashraf Suhaimi |
| author_facet | Muhd Syahir Abdul Razak Shuzlina Abdul-Rahman Mastura Hanafiah Amien Ashraf Suhaimi |
| author_sort | Muhd Syahir Abdul Razak |
| collection | DOAJ |
| description | Malaysia is currently going towards Industrial Revolution (IR) 4.0 which makes Science, Technology, Engineering and Mathematics (STEM) subjects become more crucial. IR 4.0 covers a lot of aspects especially in digital transformation in manufacturing, and this certainly requires strong mathematical knowledge. To achieve this goal, students need to have a good foundation in Mathematics subject. However, due to the increased number of students nowadays, teachers are facing challenges to track students’ progress efficiently. In this study, a predictive model has been developed that aims to assist Mathematics teachers in monitoring their students. The prototype, called MathVision, can track students’ progress effectively in each topic and subtopic of Mathematics subject and predict the grades that students will obtain based on the history result. A total of 207 instances was collected among Form 5 students from a government school to represent the samples for the modelling task. The Multiclass Decision Forest algorithm appeared to be the best predictive model with 95.16% accuracy, as compared to Boosted Decision Tree, Logistic Regression, and Neural Network. Flutter framework and Firebase services were used for front-end and back-end system respectively, and Microsoft Power BI was used for data visualization. The result of prototype testing showed that MathVision could predict students’ grade for Quiz 2 based on Quiz 1 performance. MathVision is also capable for real-time prediction that guarantees an immediate response time which can help Mathematics teachers to support students who need further assistance in this subject based on the prediction given. For MathVision’s future improvement, the number of instances needs to increase, and more significant variables need to be added. |
| first_indexed | 2024-03-09T19:23:07Z |
| format | Article |
| id | doaj.art-9f43add0b5ae46a999b6cadf50d8da52 |
| institution | Directory Open Access Journal |
| issn | 2600-8238 |
| language | English |
| last_indexed | 2024-03-09T19:23:07Z |
| publishDate | 2023-10-01 |
| publisher | UiTM Press |
| record_format | Article |
| series | Malaysian Journal of Computing |
| spelling | doaj.art-9f43add0b5ae46a999b6cadf50d8da522023-11-24T03:13:17ZengUiTM PressMalaysian Journal of Computing2600-82382023-10-01821505151610.24191/mjoc.v8i2.22391MATHVISION PROTOTYPE USING PREDICTIVE ANALYTICSMuhd Syahir Abdul Razak0Shuzlina Abdul-Rahman1Mastura Hanafiah2Amien Ashraf Suhaimi3Bitify Dynamics Sdn. Bhd., Petaling Jaya, Selangor, MalaysiaCollege of Computing Informatics and Media, Universiti Teknologi MARA, Selangor, MalaysiaAccenture Sdn. Bhd., Tun Razak Exchange, Kuala Lumpur, MalaysiaMaxis Broadband Sdn. Bhd., Menara Maxis Kuala Lumpur City Centre Off, Kuala Lumpur, Malaysia.Malaysia is currently going towards Industrial Revolution (IR) 4.0 which makes Science, Technology, Engineering and Mathematics (STEM) subjects become more crucial. IR 4.0 covers a lot of aspects especially in digital transformation in manufacturing, and this certainly requires strong mathematical knowledge. To achieve this goal, students need to have a good foundation in Mathematics subject. However, due to the increased number of students nowadays, teachers are facing challenges to track students’ progress efficiently. In this study, a predictive model has been developed that aims to assist Mathematics teachers in monitoring their students. The prototype, called MathVision, can track students’ progress effectively in each topic and subtopic of Mathematics subject and predict the grades that students will obtain based on the history result. A total of 207 instances was collected among Form 5 students from a government school to represent the samples for the modelling task. The Multiclass Decision Forest algorithm appeared to be the best predictive model with 95.16% accuracy, as compared to Boosted Decision Tree, Logistic Regression, and Neural Network. Flutter framework and Firebase services were used for front-end and back-end system respectively, and Microsoft Power BI was used for data visualization. The result of prototype testing showed that MathVision could predict students’ grade for Quiz 2 based on Quiz 1 performance. MathVision is also capable for real-time prediction that guarantees an immediate response time which can help Mathematics teachers to support students who need further assistance in this subject based on the prediction given. For MathVision’s future improvement, the number of instances needs to increase, and more significant variables need to be added.https://mjoc.uitm.edu.my/main/images/journal/vol8-2-2023/4_MATHVISION_PROTOTYPE_USING_PREDICTIVE_ANALYTICS.pdfdata analyticsir 4.0mathematicspredictive modelreal-time prediction |
| spellingShingle | Muhd Syahir Abdul Razak Shuzlina Abdul-Rahman Mastura Hanafiah Amien Ashraf Suhaimi MATHVISION PROTOTYPE USING PREDICTIVE ANALYTICS Malaysian Journal of Computing data analytics ir 4.0 mathematics predictive model real-time prediction |
| title | MATHVISION PROTOTYPE USING PREDICTIVE ANALYTICS |
| title_full | MATHVISION PROTOTYPE USING PREDICTIVE ANALYTICS |
| title_fullStr | MATHVISION PROTOTYPE USING PREDICTIVE ANALYTICS |
| title_full_unstemmed | MATHVISION PROTOTYPE USING PREDICTIVE ANALYTICS |
| title_short | MATHVISION PROTOTYPE USING PREDICTIVE ANALYTICS |
| title_sort | mathvision prototype using predictive analytics |
| topic | data analytics ir 4.0 mathematics predictive model real-time prediction |
| url | https://mjoc.uitm.edu.my/main/images/journal/vol8-2-2023/4_MATHVISION_PROTOTYPE_USING_PREDICTIVE_ANALYTICS.pdf |
| work_keys_str_mv | AT muhdsyahirabdulrazak mathvisionprototypeusingpredictiveanalytics AT shuzlinaabdulrahman mathvisionprototypeusingpredictiveanalytics AT masturahanafiah mathvisionprototypeusingpredictiveanalytics AT amienashrafsuhaimi mathvisionprototypeusingpredictiveanalytics |