Online-to-offline advertisements as field experiments

Online advertisements have become one of today's most widely used tools for enhancing businesses partly because of their compatibility with A/B testing. A/B testing allows sellers to find effective advertisement strategies such as ad creatives or segmentations. Even though several studies propose a technique to maximize the effect of an advertisement, there is insufficient comprehension of the customers' offline shopping behavior invited by the online advertisements. Herein, we study the difference in offline behavior between customers who received online advertisements and regular customers (i.e., the customers visits the target shop voluntary), and the duration of this difference. We analyzed approximately three thousand users' offline behavior with their 23.5 million location records through 31 A/B testings. We first demonstrate the externality that customers with advertisements traverse larger areas than those without advertisements, and this spatial difference lasts several days after their shopping day. We then find a long-run effect of this externality of advertising that a certain portion of the customers invited to the offline shops revisit these shops. Finally, based on this revisit effect findings, we utilize a causal machine learning model to propose a marketing strategy to maximize the revisit ratio. Our results suggest that advertisements draw customers who have different behavior traits from regular customers. This study's findings demonstrate that a simple analysis may underrate the effects of advertisements on businesses, and an analysis considering externality can attract potentially valuable customers.

[1]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[2]  Alessandro Crivellari,et al.  From Motion Activity to Geo-Embeddings: Generating and Exploring Vector Representations of Locations, Traces and Visitors through Large-Scale Mobility Data , 2019, ISPRS Int. J. Geo Inf..

[3]  Soumya K. Ghosh,et al.  THUMP: Semantic Analysis on Trajectory Traces to Explore Human Movement Pattern , 2016, WWW.

[4]  Joshua D. Angrist,et al.  Mostly Harmless Econometrics: An Empiricist's Companion , 2008 .

[5]  M. Lechner.  The Estimation of Causal Effects by Difference-in-Difference Methods , 2011 .

[6]  Avi Goldfarb,et al.  What is Different About Online Advertising? , 2014 .

[7]  Szymon Jaroszewicz,et al.  Decision trees for uplift modeling with single and multiple treatments , 2011, Knowledge and Information Systems.

[8]  Nicholas Jing Yuan,et al.  Geo-social media data analytic for user modeling and location-based services , 2016, SIGSPACIAL.

[9]  Patrick D. Surry,et al.  Real-World Uplift Modelling with Significance-Based Uplift Trees , 2012 .

[10]  Sumit Agarwal,et al.  Consumer Mobility and the Local Structure of Consumption Industries , 2017 .

[11]  Marc-Olivier Killijian,et al.  Next place prediction using mobility Markov chains , 2012, MPM '12.

[12]  Anna Monreale,et al.  WhereNext: a location predictor on trajectory pattern mining , 2009, KDD.

[13]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[14]  Padhraic Smyth,et al.  Trajectory clustering with mixtures of regression models , 1999, KDD '99.

[15]  William C. Black,et al.  Evolution of a Retail Market Area: An Event-History Model of Spatial Diffusion , 1994 .

[16]  Eric T. Bradlow,et al.  Spatial Models in Marketing , 2005 .

[17]  Peter S. Fader,et al.  Path Data in Marketing: An Integrative Framework and Prospectus for Model Building , 2009, Mark. Sci..

[18]  Ben Carterette,et al.  Do podcasts and music compete with one another? Understanding users’ audio streaming habits , 2020, WWW.

[19]  Alessandro Crivellari,et al.  Trace2trace—A Feasibility Study on Neural Machine Translation Applied to Human Motion Trajectories , 2020, Sensors.

[20]  G. D'souza,et al.  Spatial diffusion of a new loyalty program through a retail market , 2003 .

[21]  Shogo Kawanaka,et al.  Uplift modeling for location-based online advertising , 2019, LocalRec@SIGSPATIAL.

[22]  Dino Pedreschi,et al.  Time-focused clustering of trajectories of moving objects , 2006, Journal of Intelligent Information Systems.

[23]  Jing Tao,et al.  Inferring Demographics and Social Networks of Mobile Device Users on Campus From AP-Trajectories , 2017, WWW.

[24]  Qiang Gao,et al.  Predicting Human Mobility via Variational Attention , 2019, WWW.

[25]  David Card,et al.  Minimum Wages and Employment: A Case Study of the Fast Food Industry in New Jersey and Pennsylvania , 1993 .

[26]  Beibei Li,et al.  Mobile Targeting Using Customer Trajectory Patterns , 2019, Manag. Sci..

[27]  Jae-Gil Lee,et al.  Trajectory clustering: a partition-and-group framework , 2007, SIGMOD '07.

[28]  Anindya Ghose,et al.  Effectiveness of Location-Based Advertising and the Impact of Interface Design , 2020, J. Manag. Inf. Syst..

[29]  S. Fotheringham,et al.  Geographically Weighted Regression , 1998 .

[30]  Bart J. Bronnenberg.  Spatial Models in Marketing Research and Practice , 2004 .

[31]  David H. Reiley,et al.  Location, Location, Location: Repetition and Proximity Increase Advertising Effectiveness , 2016 .

[32]  Yunhao Liu,et al.  Mining Frequent Trajectory Patterns for Activity Monitoring Using Radio Frequency Tag Arrays , 2012, IEEE Transactions on Parallel and Distributed Systems.

[33]  Kunpeng Zhang,et al.  Context-aware Variational Trajectory Encoding and Human Mobility Inference , 2019, WWW.

[34]  Peter S. Fader,et al.  An Exploratory Look at Supermarket Shopping Paths , 2005 .

[35]  J. Angrist.  Mostly Harmless Econometrics , 2008 .

[36]  Albert-László Barabási,et al.  Limits of Predictability in Human Mobility , 2010, Science.

[37]  Jure Leskovec,et al.  Offline Behaviors of Online Friends , 2018, ArXiv.

[38]  Yuta Saito,et al.  Unbiased Lift-based Bidding System , 2020, ArXiv.

[39]  Joanne Hinds,et al.  What demographic attributes do our digital footprints reveal? A systematic review , 2018, PloS one.

[40]  Takuya Akiba,et al.  Optuna: A Next-generation Hyperparameter Optimization Framework , 2019, KDD.

[41]  Effectiveness of Location-Based Advertising and the Impact of Interface Design , 2020 .

[42]  Jure Leskovec,et al.  Online Actions with Offline Impact: How Online Social Networks Influence Online and Offline User Behavior , 2016, WSDM.

[43]  A. Woodside,et al.  What evokes the brand or store? Consumer research on accessibility theory applied to modeling primary choice , 1997 .

[44]  Sam K. Hui,et al.  The Effect of In-Store Travel Distance on Unplanned Spending: Applications to Mobile Promotion Strategies , 2013 .

[45]  Tomasz Kusmierczyk,et al.  On the Causal Effect of Badges , 2018, WWW.

[46]  Michael D. Smith,et al.  Location, Location, Location: An Analysis of Profitability of Position in Online Advertising Markets , 2008 .

[47]  Eric T. Bradlow,et al.  Testing Behavioral Hypotheses Using an Integrated Model of Grocery Store Shopping Path and Purchase Behavior , 2009 .

[48]  Nicholas Jing Yuan,et al.  You Are Where You Go: Inferring Demographic Attributes from Location Check-ins , 2015, WSDM.

[49]  M. Greenhut.  The Size and Shape of the Market Area of a Firm , 1952 .

[50]  Szymon Jaroszewicz,et al.  Support Vector Machines for Uplift Modeling , 2013, 2013 IEEE 13th International Conference on Data Mining Workshops.

[51]  Sam K. Hui,et al.  Deconstructing the “First Moment of Truth”: Understanding Unplanned Consideration and Purchase Conversion Using In-Store Video Tracking , 2013 .

[52]  Pierre Gutierrez,et al.  Causal Inference and Uplift Modelling: A Review of the Literature , 2017, PAPIs.

[53]  Aravind Ravi,et al.  Predicting Consumer Level Brand Preferences Using Persistent Mobility Patterns , 2018, 2018 IEEE International Conference on Big Data (Big Data).