Deal RADAR (Real-time Abandonment Detection and Recourse). Issue 5 (2nd September 2016)

• Record Type: Journal Article
• Authors: Saxena, Nishant; Arumugam, Suresh; Roy, Chiranjiv
• Is Part Of: Journal of information & optimization sciences. Volume 37:Issue 5(2016)
• Page Start: 819
• Page End: 838
• Publication Date: 2016-09-02
• Subjects: Pipeline Optimization -- Deal Abandonment -- Big Data -- Revenue Leakage -- Sales Pipeline -- Text Mining; Electronic data processing -- Periodicals; Information science -- Periodicals; Mathematical optimization -- Periodicals; 519.6
• DOI: 10.1080/02522667.2016.1191190
• Languages: English
• ISSNs: 0252-2667

Abstract

Abstract: Almost every organization faces the challenge of static or declining revenue at some point in time. Smartuse of analytics can not only turn the tides in their favour but can also catalyze some astonishing discoveries.We elucidatethe same through 'Deal RADAR'. This paper first explains how we did data discovery by combining Naïve Bayes & Hunt's Classification Algorithmsto unearth a set of neglected deals from the big unstructured sales pipeline data.We named those deals as abandoned deals and showed how they were silently leading to loss of opportunities worth millions of dollars year-over-year. This paper then explains how Deal RADAR can be deployedtodetect potential leakages in-time for effective recourse, eventually culminating in additional revenue.Deal RADAR is builton SAS® using best in class statistical techniques like KNN &Mean of n-Mode Imputation, Proximity Based Outlier Detection and Multivariate Stepwise Logistic Regression.Deal RADAR can help you optimize your sales pipeline and can not only increase your revenue but also improve your return on investment.