Using the Orange platform for data analysis

Abstract

Problem. The ability to create programs based on publicly available data to assess the preferences of individual users can be implemented, in particular, in the field of e-commerce – the knowledge of which product is best for the buyer, help to more effectively organize contextual product offerings, which in turn increases business efficiency in general. Today, users generate various data when working on the Internet. As a result, there are large amounts of different information. This information can be useful for both regular users and large companies. This makes it possible to use this data to analyze users’ preferences. One of the problems with the use of accumulated information is its crude, unstructured nature. In addition, different user groups do not need the entire data set, but their own target sample. To solve this problem today we use technologies commonly known as Bisness Intellegent (BI), and to implement it, various software products and frameworks are offered. The problem with choosing software here is to strike a balance between price and product functionality. Goal. The aim of the work is to create a data analysis system to assess consumer preferences for the use of free software. Methodology. The approaches adopted in the work to the solution of the set goal are based on the review of the approaches to the assessment of consumer preferences, the analysis of the software for the solution of the set goal. Results. The obtained results show the possibility of using the Orange data mining library to create systems for assessing consumer preferences when choosing goods and services. The library also showed good ability when working with large data sets, which is one of the main characteristics for these systems. You can also note such features of the system as the ability to work with different data formats, the ability to download data sets from the network, to use the original scripts past the standard elements. Originality. He originality is in using the Orange Data Mining Library to create data analysis systems. Practical value. The obtained results can be recommended when creating systems for analysis and work with big data.