Michel Ballings
University of Tennessee
Decision support systemAdvertisingMachine learningSupport vector machineData miningProfitability indexCustomer lifetime valueAdaBoostBusinessEconometricsLogistic regressionArtificial intelligenceMarketingRandom forestVariable (computer science)Benchmark (surveying)Data scienceMathematicsComputer scienceArtificial neural networkSocial mediaAdded valuePredictive analytics
31Publications
11H-index
496Citations
Publications 28
Newest
At the intersection of technology and marketing, the authors develop a framework to unobtrusively detect salespersons’ faces and simultaneously extract six emotions: happiness, sadness, surprise, a...
Source
#1Matthias Bogaert (UGent: Ghent University)H-Index: 4
#2Michel Ballings (UT: University of Tennessee)H-Index: 11
Last. Asil Oztekin (University of Massachusetts Lowell)H-Index: 24
view all 4 authors...
Abstract This paper aims to determine the power of social media data (Facebook and Twitter) in predicting box office sales, which platforms, data types and variables are the most important and why. To do so, we compare several models based on movie data, Facebook data, and Twitter data. We benchmark these model comparisons using various prediction algorithms. Next, we apply information-fusion sensitivity analysis to evaluate which variables are driving the predictive performance. Our analysis sh...
Source
#1Neeraj Bharadwaj (UT: University of Tennessee)H-Index: 12
#2Michel Ballings (UT: University of Tennessee)H-Index: 11
Last. Prasad A. Naik (UC Davis: University of California, Davis)H-Index: 27
view all 3 authors...
Abstract When viewers engage in cross-media consumption—view television advertising and social media posts on another medium—how do stimuli from multiple screens influence their response? To address this question, we construct a comprehensive dataset to estimate the effects of Super Bowl advertising and the advertised brands' Facebook content on ad likability. The novel insights emerging from the analyses include that: both media directly and significantly impact the response, contributing 60% a...
5 CitationsSource
#1Matthias Bogaert (UGent: Ghent University)H-Index: 4
#2Justine Lootens (UGent: Ghent University)H-Index: 1
Last. Michel Ballings (UT: University of Tennessee)H-Index: 11
view all 4 authors...
Abstract The objective of this paper is to evaluate multi-label classification techniques and recommender systems for cross-sell purposes in the financial services sector. We carried out three analyses using data obtained from an international financial services provider. First, we tested four multi-label classification techniques, of which the two problem transformation methods were combined with several base classifiers. Second, we benchmarked the performance of five state-of-the-art recommend...
6 CitationsSource
#1Matthijs MeireH-Index: 3
#2Kelly HewettH-Index: 9
Last. Dirk Van den PoelH-Index: 52
view all 5 authors...
Despite the demonstrated importance of customer sentiment in social media for outcomes such as purchase behavior and of firms’ increasing use of customer engagement initiatives, surprisingly few st...
27 CitationsSource
#1Matthias Bogaert (UGent: Ghent University)H-Index: 4
#2Michel Ballings (UT: University of Tennessee)H-Index: 11
Last. Dirk Van den Poel (UGent: Ghent University)H-Index: 52
view all 4 authors...
The main purpose of this paper is to evaluate the feasibility of predicting whether yes or no a Facebook user has self-reported to have watched a given movie genre. Therefore, we apply a data analytical framework that (1) builds and evaluates several predictive models explaining self-declared movie watching behavior, and (2) provides insight into the importance of the predictors and their relationship with self-reported movie watching behavior. For the first outcome, we benchmark several algorit...
1 CitationsSource
#1Matthias Bogaert (UGent: Ghent University)H-Index: 4
#2Michel Ballings (UT: University of Tennessee)H-Index: 11
Last. Dirk Van den Poel (UGent: Ghent University)H-Index: 52
view all 3 authors...
The purpose of this paper is to evaluate which communication types on social media are most indicative for romantic tie prediction. In contrast to analyzing communication as a composite measure, we take a disaggregated approach by modeling separate measures for commenting, liking and tagging focused on an alter’s status updates, photos, videos, check-ins, locations and links. To ensure that we have the best possible model we benchmark 8 classifiers using different data sampling techniques. The r...
9 CitationsSource
#1Michel Ballings (UT: University of Tennessee)H-Index: 11
#2Heath McCullough (UT: University of Tennessee)H-Index: 1
Last. Neeraj Bharadwaj (UT: University of Tennessee)H-Index: 12
view all 3 authors...
This research marks the first attempt to investigate the cause marketing–customer profitability relationship, and to assess whether features can moderate the influence of cause marketing (CM) on customer profitability for a focal brand and its main rival. We obtain a panel dataset on 7257 customers to evaluate the Yoplait–Susan G. Komen partnership. On a propensity score matched sample, we estimate a multilevel model and find that Yoplait’s CM initiative positively influences Yoplait’s customer ...
17 CitationsSource
#1Matthijs Meire (UGent: Ghent University)H-Index: 3
#2Michel Ballings (UT: University of Tennessee)H-Index: 11
Last. Dirk Van den Poel (UGent: Ghent University)H-Index: 52
view all 3 authors...
Abstract Business-to-business organizations and scholars are becoming increasingly aware of the possibilities social media and predictive analytics offer. Despite the interest in social media, only few have analyzed the impact of social media on the sales process. This paper takes a quantitative view to examine the added value of Facebook data in the customer acquisition process. In order to do so, we devise a customer acquisition decision support system to qualify prospects as potential custome...
19 CitationsSource
#1Matthias BogaertH-Index: 4
#2Michel BallingsH-Index: 11
Last. Dirk Van den PoelH-Index: 52
view all 4 authors...
This study assesses the feasibility of identifying self-reported sports practitioners (soccer players) on Facebook. The main goal is to develop a system to support marketers with the decision as to which prospects to target for advertising purposes. To do so, we benchmark several algorithms (i.e., random forest, logistic regression, adaboost, rotation forest, neural networks, and kernel factory) using five times twofold cross-validation. To evaluate performance and variable importances, we build...
4 CitationsSource