CUSTOMERS PROFILING BASED ON PSYCHOMETRIC CHARACTERISTICS

Apply

CUSTOMERS PROFILING BASED ON PSYCHOMETRIC CHARACTERISTICS

Journal Title: Причорноморські економічні студії - Year 2018, Vol 29, Issue 2

Abstract

In today’s world, it is important to know as much information about our customers as possible. Gender, age, occupation, family play an important role in this, but these characteristics don’t answer deeper questions, like what customer feels when making a purchase, whether it makes sense to recommend her something, what is important for the customer: brand, quality or price. To answer these questions, we are proposing in this article to use psychometric characteristic of customers, which answer these and more other questions. Psychometric characteristics are extracted from textual information, written by the customer, and shopping patterns using state-of-the-art techniques in machine learning like XGBoost, Random Forest, LSTM models. Next, these characteristics were used to mine shopping preferences and advertisement preferences.

Authors and Affiliations

T. V. Hnot

Keywords

machine learning XGBoost Random Forest LSTM OCEAN profiling psychometric

TRANSFORMATION’S MODERNIZATIONAL DETERMINANTS OF SOCIAL AND TERRITORIAL SYSTEMS IN THE CONDITIONS OF NEW REGIONALISM FORMATION IN UKRAINE

In the article, the author's definition of the region's economy modernization was given on the basis of the scientific thought genesis regarding the concept of "modernization", which should be understood not only innovat...

EP ID EP591616
DOI -
Views 95
Downloads 0