Mining Gold and Silver Using Machine Learning: Predicting Cancelled Orders at the Online Store of Tavex Norway
4
0
0
Volltext
(2) Mining Gold and Silver Using Machine Learning: Predicting Cancelled Orders at the Online Store of Tavex Norway Abstract: Widespread usage of Internet has given rise to huge amounts of online platforms, among which are e-commerce sites. Many traditionally brick-and-mortar stores, like precious metals dealers, have also opened e-commerce platforms to sell their products. Moving business online has benefits of reaching a wider audience and can be more convenient for clients. On the other hand, it has also brought along new business challenges like how to get more website users to purchase and the attempt to predict which website visitors are going to place an order during their visit. This has been a popular topic of many research papers. A less covered area in previous studies is the problem of online orders that had been already placed, but then cancelled. The cancellation problem that happens due to customers not paying for their order has been also noted in the e-commerce site of a precious metals dealer. In this work, a data analytics approach is taken to predict, whether an online order will be cancelled or not after its placement at Tavex Gull og Sølv AS. Three supervised machine algorithms, namely logistic regression, random forest and support vector machine, were used. The best achieved model had the ability to identify 68% of all unpaid orders. These results indicate that data analytics can be very promising in predicting these types of orders. Keywords: data mining, machine learning, e-commerce, cancelled orders, precious metals CERCS: P160 Statistics, operation research, programming, actuarial mathematics. Masinõppe abil kulda ja hõbedat kaevandades: tühistatud tellimuste ennustamine Tavexi e-poes Norras Lühikokkuvõte: Laialdase internetikasutuse tõttu on tekkinud palju erinevaid veebikeskkondi. Nende hulka kuuluvad ka e-poed. Paljud traditsioonilised ärid, nagu väärismetalle müüvad ettevõtted, on lisaks olemasolevatele esindustele loonud enda toodete müümiseks ka veebipoed. Ühest küljest võimaldavad need klientidel mugavamalt ostelda, teisalt pakuvad ka ärile võimaluse jõuda suurema hulga potentsiaalsete ostjateni. Ometi on see toonud firmadele ka uusi väljakutseid, näites kuidas panna üha rohkem veebilehe külastajaid ostu tegema. Paljude varasemate uurimuste eesmärk ongi olnud ennustada, kes veebilehe kasutajatest enda külastuse käigus tellimuse teevad ja mis faktorid seda otsust mõjutavad. Varasemates uurimustes on aga vähe käsitletud probleemi, mis tekib juba esitatud veebitellimuste tühistamisest. Tühistatud tellimused, ms tulenevad nende maksmata jätmisest, on probleem muuhulgas väärismetalle müüva ettevõtte Tavexi e-poes Norras. Käesolevas töös kasutatakse kolme masinõppe algoritmi – logistilist regressiooni, juhumetsa ja tugivektormasinat –, et ennustada millised Tavexi veebipoes tehtud tellimused makstakse ja millised tühistatakse. Parim saavutatud mudel suutis tuvastada 68%.
(3) kõikidest maksmata jäetud tellimustest. Töötulemused näitavad, et masinõppel on selles valdkonnas ja seda tüüpi tellimuste tuvastamiseks suur potentsiaal.. Võtmesõnad: Andmekaeve, masinõpe, e-kaubandus, tühistatud tellimused, väärismetallid CERCS: P160 Statistika, operatsioonanalüüs, programmeerimine, finants- ja kindlustusmatemaatika.
(4) Non-exclusive licence to reproduce thesis. I, Liisa Kallas. 1. herewith grant the University of Tartu a free permit (non-exclusive licence) to reproduce, for the purpose of preservation, including for the purpose of preservation the DSpace digital archives until the expiry of the term of copyright, Mining Gold and Silver Using Machine Learning: Predicting Cancelled Orders at the Online Store of Tavex Norway supervised by Rajesh Sharma, PhD. Publication of the thesis is not allowed.. 2. I am aware of the fact that the author retains the right specified in p. 1. 3. This is to certify that granting the non-exclusive licence does not infringe other persons’ intellectual property rights or rights arising from the personal data protection legislation.. 14/08/2019.
(5)
ÄHNLICHE DOKUMENTE
Cooperation between the Zoological Gardens in Copenhagen and the Zoo in Basel Switzerland was successfully established; with further financial support from a Scandinavian
To maintain a bilingual equilibrium Minett and Wang (2008) suggest a simple intervention strategy: whenever the amount of speakers of the minority language drops below some
Aiming to manage the flood risk, a protection concept in the Reuti region has been proposed by Herzog Ingenieure. It consists in adjusting the layout, the
The objective of this paper is to present results of preliminary study to examine the relationship between the thickness of the landslide mass and the height of the landslide
Airbag not released in emergency. Airbag not released in emergency. 2) Hazards are created during design. 3) Hazards are comprised of three components. 4) Hazards and mishap risk
The Member Stare to which the declaration or notification of the occupational disease was forwarded requests the Member State against which decision to refuse
Among the neglected questions in recent research we find those which concern the occasion, purpose and literary character of Barnabas. The views proposed by Windisch seem still to
The standard strategy for most museums is to physically store a work, whether that means packing selected equipment on shelves or archiving digital files on tapes, CDs or hard
