Open AccessDecision Tree: Categorizing Financial Inclusion
Author(s) -
Tanu Tiwari,
Alpana Srivastava,
Alpana Srivastava
Publication year - 2019
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.d8979.118419
Subject(s) - financial inclusion , decision tree , inclusion (mineral) , computer science , entropy (arrow of time) , analytics , population , decision tree learning , set (abstract data type) , data mining , finance , actuarial science , econometrics , financial services , mathematics , business , psychology , physics , demography , quantum mechanics , sociology , programming language , social psychology
Financial Inclusion (FI) is a global concern and even developed economies are trying to achieve complete inclusion.The inclusion index is reported by many institutions and regulatory bodies considering only one or two key attributes in their reports and hence, the impact of other financial parameters is missed. Further, the reports display an aggregated value at national level. Deciphering the inclusion at individual level will help to take corrective measures and in designing new policies. This study aims to propose a decision ruleusing techniques from data analytics to segment the population into excluded and included. The consolidated weighted scoring method was used over four key financial attributes to identify the actual class.C5.0 algorithm has been applied to arrive at the decision rule which employs technique of entropy or information gain. Surveyed data with 691 records was partitioned into training (80%) and test (20%) data sets. The classification accuracy over the test data set was found to be 100%.The findings of this study could be used by policymakers for individual estimate of FI score and prioritizing the policies