Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Predicting the next purchase date for an individual customer using machine learning
Thesis (MEng)--Stellenbosch University, 2020.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | en_ZA |
| Published: |
Stellenbosch : Stellenbosch University
2020
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613827103719424 |
|---|---|
| access_status_str | Open Access |
| author | Droomer, Marli |
| author2 | Bekker, James |
| author_browse | Bekker, James Droomer, Marli |
| author_facet | Bekker, James Droomer, Marli |
| author_sort | Droomer, Marli |
| collection | Thesis |
| dc_rights_str_mv | Stellenbosch University |
| description | Thesis (MEng)--Stellenbosch University, 2020. |
| format | Thesis |
| id | oai:scholar.sun.ac.za:10019.1/109221 |
| institution | Stellenbosch University (South Africa) |
| language | en_ZA |
| last_indexed | 2026-06-10T12:42:19.474Z |
| license_str | Other — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from SUNScholar — Stellenbosch University Repository |
| publishDate | 2020 |
| publishDateRange | 2020 |
| publishDateSort | 2020 |
| publisher | Stellenbosch : Stellenbosch University |
| publisherStr | Stellenbosch : Stellenbosch University |
| record_format | dspace |
| source_str | SUNScholar — Stellenbosch University Repository |
| spelling | oai:scholar.sun.ac.za:10019.1/109221 Predicting the next purchase date for an individual customer using machine learning Droomer, Marli Bekker, James Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering. Machine learning Predictive analytics Targeted marketing Advertising, Retail UCTD Thesis (MEng)--Stellenbosch University, 2020. ENGLISH ABSTRACT: We live in a world that is rapidly changing when it comes to technology. Gatheringa customer’s information becomes easier as companies have loyalty programs thattrack the customer’s purchasing behaviour. We live in an era where search enginessuggest your next word, online shopping is no longer scary, and people order aride by means of an application. The fact is that technology is evolving, andgathering information from customers is becoming easier. Given this change,the questions, however, are: How do companies use this information to gain acompetitive advantage? Do they use this information to benefit the customer?How can a company use customer information to give each individual a uniqueexperience?A research study was conducted to determine if an individual customer’s nextpurchase date for specific products can be predicted by means of machine learning.The focus was on fast-moving consumer goods in retail. This next purchase date canthen be used to individualise marketing to customers, which benefits the companyand the customer. In this study, the customer’s purchase history is used to train AbstractWe live in a world that is rapidly changing when it comes to technology. Gatheringa customer’s information becomes easier as companies have loyalty programs thattrack the customer’s purchasing behaviour. We live in an era where search enginessuggest your next word, online shopping is no longer scary, and people order aride by means of an application. The fact is that technology is evolving, andgathering information from customers is becoming easier. Given this change,the questions, however, are: How do companies use this information to gain acompetitive advantage? Do they use this information to benefit the customer?How can a company use customer information to give each individual a uniqueexperience?A research study was conducted to determine if an individual customer’s nextpurchase date for specific products can be predicted by means of machine learning.The focus was on fast-moving consumer goods in retail. This next purchase date canthen be used to individualise marketing to customers, which benefits the companyand the customer. In this study, the customer’s purchase history is used to trainmachine learning models. These models are then used to predict the next purchasedate for a customer-product pair. The different machine learning models that areused are recurrent neural networks, linear regression, extreme gradient boostingand an artificial neural network. Combination approaches are also investigated, andthe models are compared by the absolute error, in days, that the model predictsfrom the target variable.The artificial neural network model performed the best, predicting 31.8% of thedataset with an absolute error of less than one day, and 55% of the dataset withan absolute error of less than three days. The application of the artificial neuralnetwork as the Next Purchase Date Predictor is also demonstrated and shows howindividualised marketing can be done using the Next Purchase Date Predictor.The encouraging results of the Next Purchase Date Predictor showed that machinelearning could be used to predict the next purchase date for an individual customer. AFRIKAANSE OPSOMMING: Vandag se wˆereld is besig om baie vinnig te verander as dit kom by tegnologie. Ditraak al hoe makliker om kli ̈ente se koopgewoontes vas te vang met lojaliteitskaartewat beskikbaar is by meeste winkels. Hierdie inligting maak dit makliker om kli ̈entese koopgewoontes te analiseer. Ons bly ook in ’n wˆereld waar al hoe meer menseaanlyn aankope maak, waar ons toepassings gebruik om kos af te lewer of selfs’n toepassing gebruik om ’n rit lughawe toe te bespreek. Tegnologie ontwikkel enom inligting van kli ̈ente te versamel raak makliker. Gegewe hierdie veranderinge,laat dit ’n paar vrae: Hoe word hierdie beskikbare inligting gebruik deur besighedeom bo hulle mededingers uit te troon? Gebruik besighede hierdie inligting tot dievoordeel van hulle kli ̈ente? Hoe kan ’n besigheid hierdie inligting gebruik om virelke kli ̈ent ’n meer individuele koopervaring te gee? Om hierdie vrae te ondersoek is ’n navorsingstudie gedoen wat ondersoek ofmasjienleer gebruik kan word om te voorspel wanneer ’n kli ̈ent ’n spesifieke produkgaan aankoop. Die fokus was op vinnig-vloeiende verbruikersitems in die kleinhandel.As hierdie voorspelling gemaak kan word kan dit gebruik word om vir die kli ̈entspesifieke advertensies te skep op die spesifieke tyd wat die kli ̈ent die produk nodighet. Historiese kooptransaksies van kli ̈ente word in hierdie studie gebruik ommasjienleermodelle te skep. Hierdie modelle word dan gebruik om die voorspellingte maak vir ’n kli ̈ent-produk paar. Die verskillende masjienleermodelle wat geskep issluit in: Herhalende Neurale Netwerke, lineˆere regressie, uiterste gradientverhogingen kunsmatige neurale netwerke. Om die modelle met mekaar te vergelyk was dieabsolute fout (in dae) tussen die voorspelde waarde en die regte waarde, van aldie modelle met mekaar vergelyk. Kombinasies van verskillende modelle was ookgetoets om te kyk of dit die voorspelling kan verbeter. Die kunsmatige neurale netwerk model het die beste gevaar om die voorspellingte maak en kan 31.8% van die datastel met ’n absolute fout van minder as eendag voorspel. Verder kan dit ook 55% van die datastel met ’n absolute fout vanminder as drie dae voorspel. Die kunsmatige neurale netwerk was gekies om dievoorspeller te wees en ’n toepassing van die model word gebruik om te demonstreerhoe individuale advertensies vir kli ̈ente gegenereer kan word. Masters 2020-11-16T09:36:53Z 2021-01-31T19:40:09Z 2020-11-16T09:36:53Z 2021-01-31T19:40:09Z 2020-12 Thesis http://hdl.handle.net/10019.1/109221 en_ZA Stellenbosch University 157 pages application/pdf Stellenbosch : Stellenbosch University |
| spellingShingle | Machine learning Predictive analytics Targeted marketing Advertising, Retail UCTD Droomer, Marli Predicting the next purchase date for an individual customer using machine learning |
| title | Predicting the next purchase date for an individual customer using machine learning |
| title_full | Predicting the next purchase date for an individual customer using machine learning |
| title_fullStr | Predicting the next purchase date for an individual customer using machine learning |
| title_full_unstemmed | Predicting the next purchase date for an individual customer using machine learning |
| title_short | Predicting the next purchase date for an individual customer using machine learning |
| title_sort | predicting the next purchase date for an individual customer using machine learning |
| topic | Machine learning Predictive analytics Targeted marketing Advertising, Retail UCTD |
| url | http://hdl.handle.net/10019.1/109221 |
| work_keys_str_mv | AT droomermarli predictingthenextpurchasedateforanindividualcustomerusingmachinelearning |