ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

Employing data mining to transform sales information system into business intelligence

Miha Batič (2008) Employing data mining to transform sales information system into business intelligence. EngD thesis.

Download (1431Kb)


    These days companies have complex information systems with a vast amount of data. Amount of data increases every day. With insufficient knowledge of data, stored in company databases, the data is worthless. In this diploma I have divided data-mining algorithms into operations and described them. During the description of these algorithms and groups of algorithms I have encountered several different classifications. From among them I have chosen the most suitable one. I focused on the usage of data-mining techniques in the sales department, which is one of the basic business functions. Everybody knows sales function; we come across the sales function every day. I described possible use of data-mining in the marketing field, risk management and fraud management. I focused mainly on marketing part since it is very important activity. In the last part of this diploma I realized some of the potential uses of data-mining in Microsoft Analysis Services. I realized: - Cross-sales, Market basket analysis, - Segmentation, - Sales forecast, - Customer retention. The data from Microsoft Dynamics NAV ERP system allowed me to perform data-mining. I also discovered, that even though Microsoft Analysis Services gives us the opportunity to perform data-mining only with connecting to relational databases, we still need data warehouse in some cases. This is very much dependent on data organization in data tables. Due to a complexity and interesting details about sales function I believe that discussing sales function is very extensive. This is also the reason why I limited by only implementing possible uses of data-mining to the above four.

    Item Type: Thesis (EngD thesis)
    Keywords: Data-mining, sales, sales improvement, business intelligence, forecasting, data-mining algorithms
    Number of Pages: 63
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    doc. dr. Marko Bajec245Mentor
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=50070&select=(ID=6862164)
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 758
    Date Deposited: 11 Dec 2008 12:19
    Last Modified: 13 Aug 2011 00:34
    URI: http://eprints.fri.uni-lj.si/id/eprint/758

    Actions (login required)

    View Item