• Login
    • Library Home
    View Item 
    •   BracU IR
    • School of Data and Sciences (SDS)
    • Department of Computer Science and Engineering (CSE)
    • Thesis & Report, BSc (Computer Science and Engineering)
    • View Item
    •   BracU IR
    • School of Data and Sciences (SDS)
    • Department of Computer Science and Engineering (CSE)
    • Thesis & Report, BSc (Computer Science and Engineering)
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Prediction of success factors of FMCG commercials using signal processing and machine learning algorithms

    Thumbnail
    View/Open
    17101469, 17101124, 17101091, 16301181_CSE.pdf (1.773Mb)
    Date
    2021-06
    Publisher
    Brac University
    Author
    Saquib, Nazmus
    Mithun, Kaniz Fatema
    Tasnim, Jarin
    Sen, Pushpol
    Metadata
    Show full item record
    URI
    http://hdl.handle.net/10361/14980
    Abstract
    In the highly advanced and competitive business world, today’s marketing strategy has become very difficult. To satisfy the needs and necessities of consumers, advanced marketing research methods are required to recognize consumer’s preferences. For the purpose of product or service promotion to the mass people, companies are spending big budgets on TVCs (TV Commercials). Since the organizations are leaning towards digitized advertising at a rapid pace, effective research is required to improve the system. All the TVCs can not influence the viewers in the same way. There must be some factors that effectively increase the success rate of a TVC. For these factors to find out and make TVCs resource efficient, intensive research work in this field has been of primary priority to upgrade the industry. This kind of research is able to make a huge impression to maximize the outcome of any advertisement. Only a few literature were found on predicting TVC success factors but none of them used textual data as well as brain signal at the same time to find the factors that are most important according to our study. Although advertisement success has been a game changer for the FMCG industry lately, there is enough room to work in this industry. Since advertisements on FMCG (Fast Moving Consumer Goods) spend a comparatively bigger budget than others and it has a better influence on daily purchases of the majority of people, we decided to work on this industry particularly. In this research, we have used both the subjective and objective measurements as our dataset. Textual data taken from the interviewees as well as their brain signal extracted by EEG machine has been applied to implement the algorithms on. To predict the vital factors, we have implemented some supervised machine learning along with some deep learning algorithms like ANN and MLP to pull out our outcome. Among all of the features that we have worked on, it is found that ‘relevant message’ is the most important factor in an advertisement to convince a viewer. Including ‘relevant message’ we have taken all other crucial factors in consideration and found out the importance of the factors to make an advertisement successful. Executing machine learning methods, we have achieved highest 96% of accuracy and executing deep learning, highest 93% of accuracy was achieved. The results proves the crucial relationships between the features that we used and the advertisement success.
    Keywords
    EEG; Advertisement; FMCG; Emotion; Purchase Behaviour
     
    LC Subject Headings
    Signal processing
     
    Description
    This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2021.
     
    Cataloged from PDF version of thesis.
     
    Includes bibliographical references (pages 36-38).
    Department
    Department of Computer Science and Engineering, Brac University
    Collections
    • Thesis & Report, BSc (Computer Science and Engineering)

    Copyright © 2008-2019 Ayesha Abed Library, Brac University 
    Contact Us | Send Feedback
     

     

    Policy Guidelines

    • BracU Policy
    • Publisher Policy

    Browse

    All of BracU Institutional RepositoryCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    Statistics

    View Usage Statistics

    Copyright © 2008-2019 Ayesha Abed Library, Brac University 
    Contact Us | Send Feedback