Evaluating the Effect of Dataset Size on Predictive Model Using Supervised Learning Technique
Learning models used for prediction purposes are mostly developed without paying much cognizance to the size of datasetsthat can produce models of high accuracy and better generalization. Although, the general believe is that, large dataset is needed to construct a predictive learning model. To des...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit UMP
2015
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/6085/ http://umpir.ump.edu.my/id/eprint/6085/1/EVALUATING%20THE%20EFFECT%20OF%20DATASET%20SIZE%20ON%20PREDICTIVE%20MODEL.pdf |
| _version_ | 1848817690326597632 |
|---|---|
| author | Raheem, Ajiboye Adeleke Ruzaini, Abdullah Arshah Hongwu, Qin Kebbe, H. Isah |
| author_facet | Raheem, Ajiboye Adeleke Ruzaini, Abdullah Arshah Hongwu, Qin Kebbe, H. Isah |
| author_sort | Raheem, Ajiboye Adeleke |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | Learning models used for prediction purposes are mostly developed without paying much cognizance to the size of datasetsthat can produce models of high accuracy and
better generalization. Although, the general believe is that, large dataset is needed to construct a predictive learning model. To describe adata setas large in size, perhaps, iscircumstance dependent, thus, what constitutesa dataset to be considered as being big or small is vague.In this paper, the ability of predictive model to generalize with respect to a particular size of data when simulated with new untrained input is examined. The study experiments on three different sizes of data using Matlab programto create predictive models with a view to establishing if the sizeof data has any effect on the accuracy of a model.The simulated output of each model is measured using theMean
Absolute Error (MAE) and comparisons are made. Findings from this study reveals that, the quantity of data partitioned for the purpose of training must be of good
representation of the entire sets and sufficient enough to span through the input space. The results of simulating the three network models also shows that, the learning model
with the largest size of training setsappearsto be the most accurate and consistently delivers a much better and stable results. |
| first_indexed | 2025-11-15T01:25:46Z |
| format | Article |
| id | ump-6085 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T01:25:46Z |
| publishDate | 2015 |
| publisher | Penerbit UMP |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-60852018-05-18T02:49:20Z http://umpir.ump.edu.my/id/eprint/6085/ Evaluating the Effect of Dataset Size on Predictive Model Using Supervised Learning Technique Raheem, Ajiboye Adeleke Ruzaini, Abdullah Arshah Hongwu, Qin Kebbe, H. Isah QA76 Computer software Learning models used for prediction purposes are mostly developed without paying much cognizance to the size of datasetsthat can produce models of high accuracy and better generalization. Although, the general believe is that, large dataset is needed to construct a predictive learning model. To describe adata setas large in size, perhaps, iscircumstance dependent, thus, what constitutesa dataset to be considered as being big or small is vague.In this paper, the ability of predictive model to generalize with respect to a particular size of data when simulated with new untrained input is examined. The study experiments on three different sizes of data using Matlab programto create predictive models with a view to establishing if the sizeof data has any effect on the accuracy of a model.The simulated output of each model is measured using theMean Absolute Error (MAE) and comparisons are made. Findings from this study reveals that, the quantity of data partitioned for the purpose of training must be of good representation of the entire sets and sufficient enough to span through the input space. The results of simulating the three network models also shows that, the learning model with the largest size of training setsappearsto be the most accurate and consistently delivers a much better and stable results. Penerbit UMP 2015 Article PeerReviewed application/pdf en http://umpir.ump.edu.my/id/eprint/6085/1/EVALUATING%20THE%20EFFECT%20OF%20DATASET%20SIZE%20ON%20PREDICTIVE%20MODEL.pdf Raheem, Ajiboye Adeleke and Ruzaini, Abdullah Arshah and Hongwu, Qin and Kebbe, H. Isah (2015) Evaluating the Effect of Dataset Size on Predictive Model Using Supervised Learning Technique. International Journal of Software Engineering & Computer Sciences (IJSECS), 1. pp. 74-84. ISSN 2289-8522. (Published) http://ijsecs.ump.edu.my/images/archive/vol1/06Ajiboye_IJSECS.pdf |
| spellingShingle | QA76 Computer software Raheem, Ajiboye Adeleke Ruzaini, Abdullah Arshah Hongwu, Qin Kebbe, H. Isah Evaluating the Effect of Dataset Size on Predictive Model Using Supervised Learning Technique |
| title | Evaluating the Effect of Dataset Size on Predictive Model Using Supervised Learning Technique |
| title_full | Evaluating the Effect of Dataset Size on Predictive Model Using Supervised Learning Technique |
| title_fullStr | Evaluating the Effect of Dataset Size on Predictive Model Using Supervised Learning Technique |
| title_full_unstemmed | Evaluating the Effect of Dataset Size on Predictive Model Using Supervised Learning Technique |
| title_short | Evaluating the Effect of Dataset Size on Predictive Model Using Supervised Learning Technique |
| title_sort | evaluating the effect of dataset size on predictive model using supervised learning technique |
| topic | QA76 Computer software |
| url | http://umpir.ump.edu.my/id/eprint/6085/ http://umpir.ump.edu.my/id/eprint/6085/ http://umpir.ump.edu.my/id/eprint/6085/1/EVALUATING%20THE%20EFFECT%20OF%20DATASET%20SIZE%20ON%20PREDICTIVE%20MODEL.pdf |