• No results found

1 Prediction of retail consumer behavior

N/A
N/A
Protected

Academic year: 2021

Share "1 Prediction of retail consumer behavior"

Copied!
1
0
0

Loading.... (view fulltext now)

Full text

(1)

1

Copyright © Nepa All Rights Reserved

1 Prediction of retail consumer behavior

1.1 About Nepa

Nepa is a company at the crossroads of research, consulting and IT. We use technology and industry expertise to develop innovative and efficient research solutions that go beyond insights and enable action.

By combining survey, behavioral and business data, we make our clients truly customer- centric by tying what consumers say to what they actually do. Connecting the dots between data sets transforms the voice of the consumer into a concrete tool for decision- making with real financial impact.

Headquartered in Stockholm, we have ongoing assignments in over 50 countries across four continents. Local presence in China, Denmark, Finland, India, Singapore, Sweden and the United Kingdom ensures hands-on service for our clients.

Beyond insights, we enable action

1.2 Background

Consumer behavior prediction is essential in modern targeted advertisement systems.

Even so, there is much room for improvement in this area when it comes to brick and mortar retailers. Nepa works with some of the largest Swedish, and international, retail chains and the potential benefit of better predictions are huge. Due to this, Nepa wants to investigate the possibility to create a prediction model based on historic transaction data as well as demographic data which can accurately predict individual persons shopping need.

1.3 Goal

The goal of this master thesis is apply modern machine learning methods to determine the feasibility, and develop a model, for prediction of individual consumer’s retail behavior.

1.4 How to apply / Contact person

Send personal letter, CV, and course transcript to Daniel Malmquist (daniel.malmquist@nepa.com)

References

Related documents

To verify, we normalized the data with DESeq2 based on (a) the six established reference genes, and (b) the 33 predicted invariant genes, confirming that a non-linear correction term

The comparative chatbot compares its users to each other in order to shape user actions by surrounding people and to motivate behavior change.. The comparative chatbot was designed

The regression scores with the feature subsets selected by PCC and MI indicates that they are both able to filter out features that are less relevant to the target and

To evaluate if GetAccept fulfills the prerequisite of ensuring managerial support for data and analytics through efficient integration into marketing decision-making, the

parallelltext, övers. Rusel, The Loeb Classical Library 124, utg.. 14 Valet att använda det sociala mediet Facebook grundar sig i att det är den kanal som Parken Zoo varit som

In this study, a predictive model of the stock market using historical technical data was compared to one enhanced using social media sen- timent data in order to determine if

The central limit theorem (CLT) states that as the sample size n increases, the distribution of the sample average ¯ X of these random variables approaches the normal distribution

More specifically, the paper focuses on predicting the vote support for all major political parties in the Swedish national election by employing three simple models. This is the