Learning from machines to close the gap between funding and expenditure in the Australian National Disability Insurance Scheme
The Australian National Disability Insurance Scheme (NDIS) allocates funds to participants for purchase of services. Only one percent of the 89,299 participants spent all of their allocated funds with 85 participants having failed to spend any, meaning that most of the participants were left with un...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-04-01
|
| Series: | International Journal of Information Management Data Insights |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667096822000209 |
| _version_ | 1811244860618833920 |
|---|---|
| author | Satish Chand Yu Zhang |
| author_facet | Satish Chand Yu Zhang |
| author_sort | Satish Chand |
| collection | DOAJ |
| description | The Australian National Disability Insurance Scheme (NDIS) allocates funds to participants for purchase of services. Only one percent of the 89,299 participants spent all of their allocated funds with 85 participants having failed to spend any, meaning that most of the participants were left with unspent funds. The gap between the allocated budget and realised expenditure reflects misallocation of funds. Thus we employ alternative machine learning techniques to estimate budget and close the gap while maintaining the aggregate level of spending. Three experiments are conducted to test the machine learning models in estimating the budget, expenditure and the resulting gap; compare the learning rate between machines and humans; and identify the significant explanatory variables. Results show that machines learn “faster” than humans; machine learning models can improve the efficiency of the NDIS implementation; and significant explanatory variables identified by decision tree models and regression analysis are similar. |
| first_indexed | 2024-04-12T14:32:11Z |
| format | Article |
| id | doaj.art-1bea200a40ab4187abf65e67d29166e6 |
| institution | Directory Open Access Journal |
| issn | 2667-0968 |
| language | English |
| last_indexed | 2024-04-12T14:32:11Z |
| publishDate | 2022-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Information Management Data Insights |
| spelling | doaj.art-1bea200a40ab4187abf65e67d29166e62022-12-22T03:29:13ZengElsevierInternational Journal of Information Management Data Insights2667-09682022-04-0121100077Learning from machines to close the gap between funding and expenditure in the Australian National Disability Insurance SchemeSatish Chand0Yu Zhang1School of Business, University of New South Wales, Northcott Dr, Campbell, Canberra ACT 2612, AustraliaCorresponding author.; School of Business, University of New South Wales, Northcott Dr, Campbell, Canberra ACT 2612, AustraliaThe Australian National Disability Insurance Scheme (NDIS) allocates funds to participants for purchase of services. Only one percent of the 89,299 participants spent all of their allocated funds with 85 participants having failed to spend any, meaning that most of the participants were left with unspent funds. The gap between the allocated budget and realised expenditure reflects misallocation of funds. Thus we employ alternative machine learning techniques to estimate budget and close the gap while maintaining the aggregate level of spending. Three experiments are conducted to test the machine learning models in estimating the budget, expenditure and the resulting gap; compare the learning rate between machines and humans; and identify the significant explanatory variables. Results show that machines learn “faster” than humans; machine learning models can improve the efficiency of the NDIS implementation; and significant explanatory variables identified by decision tree models and regression analysis are similar.http://www.sciencedirect.com/science/article/pii/S2667096822000209National Disability Insurance SchemeDisability insuranceBudgetDecision makingData analyticsMachine learning |
| spellingShingle | Satish Chand Yu Zhang Learning from machines to close the gap between funding and expenditure in the Australian National Disability Insurance Scheme International Journal of Information Management Data Insights National Disability Insurance Scheme Disability insurance Budget Decision making Data analytics Machine learning |
| title | Learning from machines to close the gap between funding and expenditure in the Australian National Disability Insurance Scheme |
| title_full | Learning from machines to close the gap between funding and expenditure in the Australian National Disability Insurance Scheme |
| title_fullStr | Learning from machines to close the gap between funding and expenditure in the Australian National Disability Insurance Scheme |
| title_full_unstemmed | Learning from machines to close the gap between funding and expenditure in the Australian National Disability Insurance Scheme |
| title_short | Learning from machines to close the gap between funding and expenditure in the Australian National Disability Insurance Scheme |
| title_sort | learning from machines to close the gap between funding and expenditure in the australian national disability insurance scheme |
| topic | National Disability Insurance Scheme Disability insurance Budget Decision making Data analytics Machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S2667096822000209 |
| work_keys_str_mv | AT satishchand learningfrommachinestoclosethegapbetweenfundingandexpenditureintheaustraliannationaldisabilityinsurancescheme AT yuzhang learningfrommachinestoclosethegapbetweenfundingandexpenditureintheaustraliannationaldisabilityinsurancescheme |