Dirk Van Den Poel - Academia.edu (original) (raw)
Uploads
Papers by Dirk Van Den Poel
Social Science Research Network, 2006
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Decision Support Systems, 2017
Bookmarks Related papers MentionsView impact
This paper investigates the performance of the two novel predictors that capture the dynamics of ... more This paper investigates the performance of the two novel predictors that capture the dynamics of the bankruptcy process expressed in the sequences of financial ratios: (1) predictors based on Markov for Discrimination, and (2) predictors based on clustering of similar sequences of financial ratios. The results show the superb performance of the novel predictors in terms of the 5-percent and 10-percent lift, when benchmarked with more traditional sequential and non-sequential predictors.
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Decision Support Systems, 2021
Bookmarks Related papers MentionsView impact
Recently, the consumer credit industry has experienced a sizeable growth, where scoring technique... more Recently, the consumer credit industry has experienced a sizeable growth, where scoring techniques have grown to outperform the traditional, judgmental manner of assessing credit risk. Using the data of a Belgian direct-mail company offering consumer credit, the authors have shown a clear improvement in comparison with its current credit evaluation system, constructed by an international company specialized in consumer credit scoring, and identify the size of this performance increase due to population drift versus model improvement. Considering the crucial impact of the accuracy of the score on the cost side (lowered credit risk) as well as on the revenue side (increased accepted applications), in this study, we highlight the importance of introducing different performance measures to quantify credit risk performance. Hence, instead of reporting predictive performance on the total sample, we have quantified the predictive performance in more detail into a graphical overview that ca...
Bookmarks Related papers MentionsView impact
Computers and Electronics in Agriculture, 2021
Abstract Existing lactation models predict milk yields based on a fixed amount of observed milk p... more Abstract Existing lactation models predict milk yields based on a fixed amount of observed milk production in early lactation. In contrast, this study proposes a model to predict the entire lactation curve of dairy cows by leveraging historical milk yield information observed in the preceding cycle. More specifically, we present a deep learning framework to encode the model inputs, predict the latent representation of the milk yield sequences and generate the corresponding lactation curves. Results show that the proposed framework outperforms the baseline models and that during the first 26 days of lactation, the model’s predictions are more accurate than those of a state-of-the-art lactation model which is able to leverage the observed milk yields. As a result, the framework presented in this study allows farmers to increase their forecast horizon with respect to predicting its herd’s total production and hence facilitates optimal herd management. Additionally, the model can be used to compare a cow’s actual and expected milk yield over the entire course of the lactation cycle. This in turn can help to accelerate disease detection and enhance current animal monitoring systems. Finally, as the model incorporates the impact of health and reproduction events as well as herd management on the cow’s productivity, future earnings and costs can be estimated more accurately.
Bookmarks Related papers MentionsView impact
Decision Support Systems, 2016
Bookmarks Related papers MentionsView impact
Journal of Applied Econometrics, 2015
Bookmarks Related papers MentionsView impact
Over the past two decades, the financial markets have become more competitive resulting in dimini... more Over the past two decades, the financial markets have become more competitive resulting in diminishing profit margins and blurring distinctions between banks, insurers and brokerage firms. Hence, nowadays a small number of large institutions offering a wider set of services dominate the financial-services industry. These developments stimulated the implementation of Customer Relationship Management (CRM). Given the increasing customer-acquisition cost, marketers realize that the best prospects for the sales of current and new financial services are the current customers. So cross-sell actions are created to motivate existing customers to use additional services from the firm. A great opportunity lies in cross-selling insurance products to bank clients and vice versa. In this study, we investigate purchase patterns of financial services from an international financial institution to identify cross-selling opportunities. We introduce the Mixture Transition Distribution model (MTD) as a parsimonious alternative to the Markov model enabling the estimation of high-order Markov chains and facilitating the interpretation by providing a much smaller transition matrix and lag parameters. Our results are in favor of the MTD model.
Bookmarks Related papers MentionsView impact
The management of coupon promotions is an important issue since it is still one of the major prom... more The management of coupon promotions is an important issue since it is still one of the major promotion media. Although new distribution channels arise, the allocation of coupons does not go without problems. Companies are investing thoroughly in an attempt to convince as many customers as possible to buy their products. This results in a competitive battle between retailers and manufacturers since both target the same customer base. In this paper the methodology used by retailers and manufacturers to determine their target selection for promotional actions is improved by building separate predictive models for the same customer base. One model makes predictions concerning the redemption behavior of promotions that are distributed by the retailer while another model does the same for promotions issued by manufacturers. A logistic regression is used to predict coupon redemption behavior. The performance of the models will be quantified by the classification accuracy and the area under...
Bookmarks Related papers MentionsView impact
European Journal of Operational Research, 2019
Bookmarks Related papers MentionsView impact
ensemble classifiers for binary classification (De Bock et al.,2010). The ensembles implement
Bookmarks Related papers MentionsView impact
ISPRS International Journal of Geo-Information, 2021
This article assesses whether ambient population is a more suitable population-at-risk measure fo... more This article assesses whether ambient population is a more suitable population-at-risk measure for crime types with mobile targets than residential population for the purpose of intelligence-led policing applications. Specifically, the potential use of ambient population as a crime rate denominator and predictor for predictive policing models is evaluated, using mobile phone data (with a total of 9,397,473 data points) as a proxy. The results show that ambient population correlates more strongly with crime than residential population. Crime rates based on ambient population designate different problem areas than crime rates based on residential population. The prediction performance of predictive policing models can be improved by using ambient population instead of residential population. These findings support that ambient population is a more suitable population-at-risk measure, as it better reflects the underlying dynamics in spatiotemporal crime trends. Its use has therefore mu...
Bookmarks Related papers MentionsView impact
IEEE Access, 2021
Bookmarks Related papers MentionsView impact
IEEE Access, 2021
Bookmarks Related papers MentionsView impact
Scandinavian Journal of Economics, 2010
Bookmarks Related papers MentionsView impact
Journal of Product Innovation Management, 2017
Bookmarks Related papers MentionsView impact
Decision Analysis
Bookmarks Related papers MentionsView impact
Social Science Research Network, 2006
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Decision Support Systems, 2017
Bookmarks Related papers MentionsView impact
This paper investigates the performance of the two novel predictors that capture the dynamics of ... more This paper investigates the performance of the two novel predictors that capture the dynamics of the bankruptcy process expressed in the sequences of financial ratios: (1) predictors based on Markov for Discrimination, and (2) predictors based on clustering of similar sequences of financial ratios. The results show the superb performance of the novel predictors in terms of the 5-percent and 10-percent lift, when benchmarked with more traditional sequential and non-sequential predictors.
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Decision Support Systems, 2021
Bookmarks Related papers MentionsView impact
Recently, the consumer credit industry has experienced a sizeable growth, where scoring technique... more Recently, the consumer credit industry has experienced a sizeable growth, where scoring techniques have grown to outperform the traditional, judgmental manner of assessing credit risk. Using the data of a Belgian direct-mail company offering consumer credit, the authors have shown a clear improvement in comparison with its current credit evaluation system, constructed by an international company specialized in consumer credit scoring, and identify the size of this performance increase due to population drift versus model improvement. Considering the crucial impact of the accuracy of the score on the cost side (lowered credit risk) as well as on the revenue side (increased accepted applications), in this study, we highlight the importance of introducing different performance measures to quantify credit risk performance. Hence, instead of reporting predictive performance on the total sample, we have quantified the predictive performance in more detail into a graphical overview that ca...
Bookmarks Related papers MentionsView impact
Computers and Electronics in Agriculture, 2021
Abstract Existing lactation models predict milk yields based on a fixed amount of observed milk p... more Abstract Existing lactation models predict milk yields based on a fixed amount of observed milk production in early lactation. In contrast, this study proposes a model to predict the entire lactation curve of dairy cows by leveraging historical milk yield information observed in the preceding cycle. More specifically, we present a deep learning framework to encode the model inputs, predict the latent representation of the milk yield sequences and generate the corresponding lactation curves. Results show that the proposed framework outperforms the baseline models and that during the first 26 days of lactation, the model’s predictions are more accurate than those of a state-of-the-art lactation model which is able to leverage the observed milk yields. As a result, the framework presented in this study allows farmers to increase their forecast horizon with respect to predicting its herd’s total production and hence facilitates optimal herd management. Additionally, the model can be used to compare a cow’s actual and expected milk yield over the entire course of the lactation cycle. This in turn can help to accelerate disease detection and enhance current animal monitoring systems. Finally, as the model incorporates the impact of health and reproduction events as well as herd management on the cow’s productivity, future earnings and costs can be estimated more accurately.
Bookmarks Related papers MentionsView impact
Decision Support Systems, 2016
Bookmarks Related papers MentionsView impact
Journal of Applied Econometrics, 2015
Bookmarks Related papers MentionsView impact
Over the past two decades, the financial markets have become more competitive resulting in dimini... more Over the past two decades, the financial markets have become more competitive resulting in diminishing profit margins and blurring distinctions between banks, insurers and brokerage firms. Hence, nowadays a small number of large institutions offering a wider set of services dominate the financial-services industry. These developments stimulated the implementation of Customer Relationship Management (CRM). Given the increasing customer-acquisition cost, marketers realize that the best prospects for the sales of current and new financial services are the current customers. So cross-sell actions are created to motivate existing customers to use additional services from the firm. A great opportunity lies in cross-selling insurance products to bank clients and vice versa. In this study, we investigate purchase patterns of financial services from an international financial institution to identify cross-selling opportunities. We introduce the Mixture Transition Distribution model (MTD) as a parsimonious alternative to the Markov model enabling the estimation of high-order Markov chains and facilitating the interpretation by providing a much smaller transition matrix and lag parameters. Our results are in favor of the MTD model.
Bookmarks Related papers MentionsView impact
The management of coupon promotions is an important issue since it is still one of the major prom... more The management of coupon promotions is an important issue since it is still one of the major promotion media. Although new distribution channels arise, the allocation of coupons does not go without problems. Companies are investing thoroughly in an attempt to convince as many customers as possible to buy their products. This results in a competitive battle between retailers and manufacturers since both target the same customer base. In this paper the methodology used by retailers and manufacturers to determine their target selection for promotional actions is improved by building separate predictive models for the same customer base. One model makes predictions concerning the redemption behavior of promotions that are distributed by the retailer while another model does the same for promotions issued by manufacturers. A logistic regression is used to predict coupon redemption behavior. The performance of the models will be quantified by the classification accuracy and the area under...
Bookmarks Related papers MentionsView impact
European Journal of Operational Research, 2019
Bookmarks Related papers MentionsView impact
ensemble classifiers for binary classification (De Bock et al.,2010). The ensembles implement
Bookmarks Related papers MentionsView impact
ISPRS International Journal of Geo-Information, 2021
This article assesses whether ambient population is a more suitable population-at-risk measure fo... more This article assesses whether ambient population is a more suitable population-at-risk measure for crime types with mobile targets than residential population for the purpose of intelligence-led policing applications. Specifically, the potential use of ambient population as a crime rate denominator and predictor for predictive policing models is evaluated, using mobile phone data (with a total of 9,397,473 data points) as a proxy. The results show that ambient population correlates more strongly with crime than residential population. Crime rates based on ambient population designate different problem areas than crime rates based on residential population. The prediction performance of predictive policing models can be improved by using ambient population instead of residential population. These findings support that ambient population is a more suitable population-at-risk measure, as it better reflects the underlying dynamics in spatiotemporal crime trends. Its use has therefore mu...
Bookmarks Related papers MentionsView impact
IEEE Access, 2021
Bookmarks Related papers MentionsView impact
IEEE Access, 2021
Bookmarks Related papers MentionsView impact
Scandinavian Journal of Economics, 2010
Bookmarks Related papers MentionsView impact
Journal of Product Innovation Management, 2017
Bookmarks Related papers MentionsView impact
Decision Analysis
Bookmarks Related papers MentionsView impact