Extrapolative Data Analytics as a Panacea for Business Intelligence Decisions in Auto Dealership: A Case Study
Document Type
Event
Abstract
The application of business intelligence (BI) in data analytics helps organizations access critical information in multiple areas including sales, finance, marketing, etc. However, there is a dearth of strategies to effectively leverage BI to empower businesses to increase actionable data, provide great insights into the industry trends and facilitate a more strategically geared decision-making model. This study implemented predictive data analytics to determine how the subjective decision-making process of certified used dealership management is conducted in their approach to sales of vehicles and other business variable decisions. Scouring over forty-five different aspects of typical vehicle items, the study randomly selected twelve (12) features considered important using the Contingency Table Method (CTM) and the Support Vector Machine (SVM). The determinant of which resulted in their comparison to test their algorithm accuracies on different variables and using machine learning equations to create a model. When six data mining methods are applied to test, the Support Vector Machine (SVM) prediction model performs the best. The SVM model provides an accuracy of almost 85% in predicting analytics whether a certified used vehicle would be successfully sold within an acceptable duration of time. In contrast, the extrapolative accuracy of the current decision-making process compared showed relative statistics of just around 50%. The study concludes that implementing business intelligence (BI) using predictive data analytics and its machine learning models leads to improved decision making, an increase in revenue, an improvement in customer satisfaction, and an increase in market share.
Extrapolative Data Analytics as a Panacea for Business Intelligence Decisions in Auto Dealership: A Case Study
Breakout Session A: Computer and Data Sciences
CASB 102The application of business intelligence (BI) in data analytics helps organizations access critical information in multiple areas including sales, finance, marketing, etc. However, there is a dearth of strategies to effectively leverage BI to empower businesses to increase actionable data, provide great insights into the industry trends and facilitate a more strategically geared decision-making model. This study implemented predictive data analytics to determine how the subjective decision-making process of certified used dealership management is conducted in their approach to sales of vehicles and other business variable decisions. Scouring over forty-five different aspects of typical vehicle items, the study randomly selected twelve (12) features considered important using the Contingency Table Method (CTM) and the Support Vector Machine (SVM). The determinant of which resulted in their comparison to test their algorithm accuracies on different variables and using machine learning equations to create a model. When six data mining methods are applied to test, the Support Vector Machine (SVM) prediction model performs the best. The SVM model provides an accuracy of almost 85% in predicting analytics whether a certified used vehicle would be successfully sold within an acceptable duration of time. In contrast, the extrapolative accuracy of the current decision-making process compared showed relative statistics of just around 50%. The study concludes that implementing business intelligence (BI) using predictive data analytics and its machine learning models leads to improved decision making, an increase in revenue, an improvement in customer satisfaction, and an increase in market share.