• A survey on mobile data uses

      Colot, Christian; Linden, Isabelle; Baecke, Philippe (International Journal of Decision Support System Technology, 2016)
      Mobile devices leave an unprecedented volume and variety of digital traces of human beings. In this paper, the authors propose an overview of multiple uses of mobile data published in the scientific literature. The organization of the survey follows a typology built on two criteria: interaction level and focus of analysis. Crossing these two dimensions would suggest 8 research areas. Only 4 of them are actually covered by the collected pieces of work. They are discussed in turn showing off the main characteristics of them. Finally, the discussion of the 4 remaining areas highlights new research areas with a special focus on the possibility to use mobile data to influence individual users towards efficient collective behaviors. To conclude, current and future research avenues suggest that mobile devices and their underlying data are likely to be employed in many domains and may be used not only to observe human life but also to influence it.
    • Addressable ads are shaping the future of TV Marketing. Combining the benefits of digital advertising with the power of the big screen

      De Schaepdrijver, Leen; Baecke, Philippe; Tackx, Koen; Coeymans, Jeroen; Lauwers, Lode; Van Driessche, Bert (2021)
      Combining the benefits of digital advertising with the power of the big screen With the rise of digital media and big data, the media landscape has gone through turbulent times. Technology is developing more rapidly than ever, and we are now able to collect and process data in volumes and formats that we never could before. Digital companies were the first to jump on this train of technological revolution and are now harnessing the power of data. Where the TV landscape had barely changed during the past decades, it is now feeling the heat of digitisation. Digital channels are offering interesting alternatives to linear TV in terms of content and experience, and digital advertising has been growing exponentially during the last decade. In turn, TV has reacted with digital initiatives of its own, blurring the distinction between traditional media and digital media. Nonetheless, there is still a long road ahead before they get to par with the tech giants and truly adopt a technology- and data-driven way of working. It is safe to say that digitisation has shaken the entire TV ecosystem to its foundations. Various factors are threatening the comfortable position that TV advertising has been in for the last few decades. Both consumers and marketers are changing their behaviour and expectations, and digital advertising is taking advantage of this new vacuum by answering their needs. When looking for opportunities to try and combat the dominance of big tech, ‘addressable advertising’ might be the answer. This innovative advertising technique on TV brings together the benefits of TV advertising and those of digital advertising. Combining the best of both worlds, addressable advertising makes it possible to target specific households via their set top box with TV ads, whilst at the same time offering opportunities to improve campaign measurement. However, there are still some challenges ahead such as scale, standardisation, cost and general inertia. And as addressable advertising is highly data-driven, this advertising technique is also closely linked to the challenging topic of privacy and ethics. In order to get access to data, companies will have to give their customers enough value in return for their data.
    • An empirical investigation on the value of combined judgmental and statistical forecasting

      De Baets, Shari; Baecke, Philippe; Vanderheyden, Karlien (2014)
    • Bluetooth tracking of humans in an indoor environment: An application to shopping mall visits

      Oosterlinck, Dieter; Benoit, Dries F.; Baecke, Philippe; Van de Weghe, Nico (Applied Geography, 2017)
      Intelligence about the spatio-temporal behaviour of individuals is valuable in many settings. Generating tracking data is a necessity for this analysis and requires an appropriate methodology. In this study, the applicability of Bluetooth tracking in an indoor setting is investigated. A wide variety of applications can benefit from indoor Bluetooth tracking. This paper examines the value of the method in a marketing application. A Belgian shopping mall served as a real-life test setting for the methodology. A total of 56 Bluetooth scanners registered 18.943 unique MAC addresses during a 19-day period. The results indicate that Bluetooth tracking is a sound approach for capturing tracking data, which can be used to map and analyse the spatio-temporal behaviour of individuals. The methodology also provides a more efficient and more accurate way of obtaining a variety of relevant metrics in the field of consumer behaviour research. Bluetooth tracking can be implemented as a new and cost effective practice for marketing research, that provides fast and accurate results and insights. We conclude that Bluetooth tracking is a viable approach, but that certain technological and practical aspects need to be considered when applying Bluetooth tracking in new cases.
    • Consumer brand value and advocacy drivers of a telecom brand

      De Berti, Freya; Goedertier, Frank; Baecke, Philippe (2014)
    • Data Augmentation by predicting spending pleasure using commercially available external data

      Baecke, Philippe; Van den Poel, Dirk (Journal of Intelligent Information Systems, 2011)
    • Data augmentation by predicting spending pleasure using commercially available external data

      Baecke, Philippe; Van den Poel, Dirk (2009)
      Type-ins are interactive online ads in which the user must enter some information, such as a brand message, into a text box in order to access additional content or submit information via a form on a website. We compared type-in ads to more traditional static ads in two places on a website: as an interstitial, in which users must view the ad to get to the next page of content, and as a form ad, in which users must view an ad to submit an online form. There was a significant increase in brand and message recall for type-ins compared to static ads for both interstitials and form ads. Furthermore, type-ins did not impact user experience positively or negatively in either case. Both interstitial and form ads, whether type-in or static, had better brand and message recall when the ad and site content were consistent (i.e., an entertainment ad on an entertainment site) than when the ad was inconsistent (i.e., a travel ad on an entertainment site). The increased recall for brand and message produced with type-in ads indicates that type-ins can play an important role in the broader goals of brand building within IMC. [ABSTRACT FROM AUTHOR] Copyright of International Journal of Integrated Marketing Communications is the property of Racom Communications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
    • Data-driven vehicle routing with profits

      Vercamer, D.; Baecke, Philippe; Gendreau, M.; Van den Poel, Dirk (2015)
    • Developing a maturity assessment model for demand forecasting

      Vereecke, Ann; Vanderheyden, Karlien; Baecke, Philippe; Van Steendam, Tom (2016)
    • From one-class to two-class classification by incorporating expert knowledge

      Oosterlinck, Dieter; Benoit, Dries F.; Baecke, Philippe (2018)
      In certain business cases the aim is to identify observations that deviate from an identified normal behaviour. It is often the case that only instances of the normal class are known, whereas so called novelties are undiscovered. Novelty detection or anomaly detection approaches usually apply methods from the field of outlier detection. However, anomalies are not always outliers and outliers are not always anomalies. The standard one-class classification approaches therefore underperform in many real business cases. Drawing upon literature about incorporating expert knowledge,we come up with a new method that significantly improves the predictive performance of a one-class model. Combining the available data and expert knowledge about potential anomalies enables us to create synthetic novelties. The latter are incorporated into a standard two-class predictive model. Based on a telco dataset, we prove that our synthetic two-class model clearly outperforms a standard one-class model on the synthetic dataset. In a next step the model was applied to real data. Top identified novelties were manually checked by experts. The results indicate that incorporating expert knowledge to transform a one-class problem into a two-class problem is a valuable method.
    • From one-class to two-class classification by incorporating expert knowledge: Novelty detection in human behaviour

      Oosterlinck, Dries; Benoit, Dries F.; Baecke, Philippe (European Journal of Operational Research, 2020)
      One-class classification is the standard procedure for novelty detection. Novelty detection aims to identify observations that deviate from a determined normal behaviour. Only instances of one class are known, whereas so called novelties are unlabelled. Traditional novelty detection applies methods from the field of outlier detection. These standard one-class classification approaches have limited performance in many real business cases. The traditional techniques are mainly developed for industrial problems such as machine condition monitoring. When applying these to human behaviour, the performance drops significantly. This paper proposes a method that improves existing approaches by creating semi-synthetic novelties in order to have labelled data for the two classes. Expert knowledge is incorporated in the initial phase of this data generation process. The method was deployed on a real-life test case where the goal was to detect fraudulent subscriptions to a telecom family plan. This research demonstrates that the two-class expert model outperforms a one-class model on the semi-synthetic dataset. In a next step the model was validated on a real dataset. A fraud detection team of the company manually checked the top predicted novelties. The results show that incorporating expert knowledge to transform a one-class problem into a two-class problem is a valuable method.
    • Home location prediction with telecom data: Benchmarking heuristics with a predictive modelling approach

      Oosterlinck, Dieter; Baecke, Philippe; Benoît, Dries (Expert Systems with Applications, 2020)
      Correctly identifying the home location is crucial for human mobility analysis with telecom data, more specifically call detail record (CDR) data. To that end, multiple heuristics have been developed in literature. Nevertheless, due to the lack of ground truth home location data, no study has thoroughly validated these widely used methods so far. We present a detailed performance analysis of existing home detection heuristics, using a unique dataset that enables this important validation on the lowest level, being the level of the cell tower. Our research indicates that simple heuristics surprisingly outperform their more complex counterparts. The benchmark study revealed that the best heuristic is able to identify the home location with an average error of approximately 4.5 kilometres and selects the correct home tower in 60.69% of the cases. Based on the insights provided by our study, we propose a new heuristic that increases the accuracy to 61% and lowers the average distance error to 4.365 kilometres. Secondly, if the home location is known for possibly only a fraction of the instances, we propose a labelled predictive modelling approach. Adding social network based variables in this predictive model further enhances the predictive performance. Our best model reduces the average distance error to 2.848 kilometres and selects the correct home location in 72.08% of the cases. Furthermore, this result provides an indication of the upper bound for home detection with CDR data. Finally, models that only make use of social network based data are developed as well. Results show that even without using data of the focal individual, these models are able to select the correct home tower in 37.65% of the cases and achieve an average distance error of 8.1 kilometres.
    • How customer referral programs harness the power of your customers' friendships

      Roelens, Iris; Baecke, Philippe; Benoit, Dries F.; Van den Bulte, Christophe (2017)
    • Identifying influencers in a social network

      Roelens, Iris; Baecke, Philippe; Benoit, Dries F. (2016)
    • Identifying influencers in a social network using customer referral behaviour

      Roelens, Iris; Baecke, Philippe; Benoit, Dries F. (2016)
    • Identifying influencers in a social network: the value of real referral data

      Roelens, Iris; Baecke, Philippe; Benoit, Dries F. (Decision Support Systems, 2016)
      Individuals influence each other through social interactions and marketers aim to leverage this interpersonal influence to attract new customers. It still remains a challenge to identify those customers in a social network that have the most influence on their social connections. A common approach to the influence maximization problem is to simulate influence cascades through the network based on the existence of links in the network using diffusion models. Our study contributes to the literature by evaluating these principles using real-life referral behaviour data. A new ranking metric, called Referral Rank, is introduced that builds on the game theoretic concept of the Shapley value for assigning each individual in the network a value that reflects the likelihood of referring new customers. We also explore whether these methods can be further improved by looking beyond the one-hop neighbourhood of the influencers. Experiments on a large telecommunication data set and referral data set demonstrate that using traditional simulation based methods to identify influencers in a social network can lead to suboptimal decisions as the results overestimate actual referral cascades. We also find that looking at the influence of the two-hop neighbours of the customers improves the influence spread and product adoption. Our findings suggest that companies can take two actions to improve their decision support system for identifying influential customers: (1) improve the data by incorporating data that reflects the actual referral behaviour of the customers or (2) extend the method by looking at the influence of the connections in the two-hop neighbourhood of the customers.
    • Improving customer acquisition models by incorporating spatial autocorrelation at different levels of granularity

      Baecke, Philippe; Van den Poel, Dirk (Journal of Intelligent Information Systems, 2013)
      Traditional CRM models often ignore the correlation that could exist among the purchasing behavior of surrounding prospects. Hence, a generalized linear autologistic regression model can be used to capture this interdependence and improve the predictive performance of the model. In particular, customer acquisition models can benefit from this. These models often suffer from a lack of data quality due to the limited amount of information available about potential new customers. Based on a customer acquisition model of a Japanese automobile brand, this study shows that the extra value resulting from incorporating neighborhood effects can vary significantly depending on the granularity level on which the neighborhoods are composed. A model based on a granularity level that is too coarse or too fine will incorporate too much or too little interdependence resulting in a less than optimal predictive improvement. Since neighborhood effects can have several sources (i.e. social influence, homophily and exogeneous shocks), this study suggests that the autocorrelation can be divided into several parts, each optimally measured at a different level of granularity. Therefore, a model is introduced that simultaneously incorporates multiple levels of granularity resulting in even more accurate predictions. Further, the effect of the sample size is examined. This shows that including spatial interdependence using finer levels of granularity is only useful when enough data is available to construct stable spatial lag effects. As a result, extending a spatial model with multiple granularity levels becomes increasingly valuable when the data sample becomes larger.
    • Improving customer acquisition models by incorporating spatial autocorrelation at different levels of granularity

      Baecke, Philippe; Van den Poel, Dirk (2012)
      Several academic studies have been conducted to explore the link between taxes on tobacco products and consumption behavior, especially smoking cessation. While most research has been conducted by comparing static levels of taxation across states or countries, almost none have looked at the dynamic effects of taxes, let alone the context of a tax decrease that is non-homogeneous within a given country, alongside parallel phenomena such as resort to smuggling. Moreover, most research has failed to adopt a contingency framework taking into account potentially influent variables such as age and consumption levels. Using a unique dataset compiled by Statistics Canada, we estimate several models that explore consumers’ behavior towards cigarettes as taxes are rolled back, their resort to consuming smuggled products, as well as a range of individual factors that influence said behaviors. We show effects in the very short term - that is, right after taxes are decreased - and in the long term - that is, a little over one year after taxes have been rolled back. Our results suggest that consumption of smuggled cigarettes is directly and strongly linked to the level of taxes and that this behavior can be efficiently curbed by tax reduction. Tax cuts explain in the range of 17% a smoker’s decision to stop regularly consuming smuggled cigarettes. In addition, our results suggest that taxes themselves play a very limited role in explaining individuals’ propensity to quit or to start smoking, especially in comparison with age and current smoking levels. Our analyses show that, despite statistically significant effects attributable to the large sample size, the part of a smoker or non-smoker behavior that is explained by taxes is very small. In other words, while cigarette tax cuts do reduce propensity to quit or to remain a non-smoker, especially in the long run, they are responsible for about ½ of 1% of this decision. In comparison, models that take into account respondent age or, for smokers, the average number of cigarettes smoked daily, can explain in the order of 5% to 10% the variation in behavior - that is, 10 to 20 times as much as taxes only. These results suggest that, despite their statistically significant influence on smokers and non-smokers behavioral changes, tax cuts from an original level as high as $21 on a carton of 200 cigarettes are not key short-term and long-term behavioral change agents - that is, when taxes are that high, and in a context where about 20% of the population does smoke, tax cuts neither strongly induce non-smokers to start smoking nor strongly induce smokers not to quit smoking. However, they do, where smuggled products are readily available, strongly decrease smokers’ consumption of smuggled cigarettes. This should warrant further investigation of more effective means to curb smoking in this context, such as societal marketing efforts raising awareness of the short- and long-term health hazards associated with smoking