Fraudulent behaviour are suspicious activities that usually occur before a crime takes place. These suspicious activities are being carried out on a day-to-day basis in banks, supermarkets, restaurants, Bus stop, offices, residential buildings, companies e.t.c. Within the banking industry, fraudulent behaviour is when a customer or a person makes suspicious moves before committing a crime. In this paper, an online predictive system for mapping visual scene against fraudulent behaviour was developed. The dataset for this system was collected from Kaggle database. The analysis of the video clips gave a total of 427 frames, 380 was visually mapped to be of fraudulent behaviour while 47 was being mapped to be of normal behaviour. These frames were used in training a convolutional neural network for detecting fraudulent behaviour from a video clip. The proposed model was deployed to web using python and flask framework. Our result gave about 99.99%. The proposed system was compared with that of Nakib et.al. (2018). The result of Nakib et.al. (2018) gave an accuracy of about 90.2% while that of our proposed system gave 99.99%.

Fraudulent Behaviour, Visual Scenes, Surveillance Camera, Deep Learning

[1]. S. Jatav, V. Sharma, “An algorithm for predictive data mining approach in medical diagnosis”, International Journal of Computer Science & Information Technology (IJCSIT) Vol, 10., 2018.
[2]. B. E. Aguinaldo, “21st Century Learning Skills Predictive Model Using PART Algorithm”, In Proceedings of the 3rd International Conference on Machine Learning and Soft Computing, pp. 134-137, 2019.
[3]. T. Davenport, A. Guha, D. Grewal, T. Bressgott, “How artificial intelligence will change the future of marketing”, Journal of the Academy of Marketing Science, 48(1), 24-42, 2020.
[4]. M. Zawawi, K. Jusoff, A. Rahman, “Behavioral intention for fraudulent reporting behaviour using cognitive theory”. Asian Social Science, 4(7), 43-47, 2008
[5]. W. W. Eckerson, “Predictive analytics. Extending the Value of Your Data Warehousing Investment”, TDWI Best Practices Report, 1, 1-36, 2007.
[6]. A. Grawal, J.S. Gans, A. Goldfarb, “Exploring the impact of artificial intelligence: Prediction versus judgment”, Information Economics and Policy, 47, 1-6, 2018.
[7]. A. Sell, A, “The Same Old Story: Predictive Algorithms and the Novel”. tba: Journal of Art, Media, and Visual Culture, 2(1), 49-58.2020
[8]. W.H. Smith, M. Milford, K. D. McDonald-Maier, S. Ehsan, S., “Scene Retrieval for Contextual Visual Mapping”. arXiv preprint arXiv:2102.12728, 2021
[9]. M. Nakib, R. Khan, M. Hasan, J. Uddin, J, “Crime scene prediction by detecting threatening objects using convolutional neural network”, In International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2), pp. 1-4, 2018. IEEE.
[10]. T. Chandrakala, S. Nirmala, K. Dharmarajan, K. Selvam K, “Development Of Crime And Fraud Prediction Using Data Mining Approaches”., International Journal of Advanced Research in Engineering and Technology (IJARET) Vol.11, Issue 12, pp. 1450-1470, December 2020.
[11] P. Stalidis, T. Semertzidis, P. Daras, “Examining Deep Learning Architectures for Crime Classification and Prediction”, Forecasting. 3(4): 741-762, 2021.
https://doi.org/10.3390/forecast3040046.
[12] M. Merylin, M. Stéphanie, C. Scarpazza, G. Nicolò, “Detecting deception through facial expressions in a dataset of videotaped interviews: A comparison between human judges and machine learning models”, Computers in Human Behaviour. 127, 2022. https://doi.org/10.1016/j.chb.2021.107063.
[13] S. Aruljothi, K. Pavithradevi, “Detection Of Suspicious Activities In Public Areas Using Staged Matching Technique”, International Journal Of Advanced Information And Communication Technology. 1(1), 140-143, 2014
[14] G. Vallathan, A. John, C. Thirumalai, S. Mohan, G. Srivastava, “Suspicious activity detection using deep learning in secure assisted living IoT environments”, The Journal of Supercomputing. doi:10.1007/s11227-020-03387-8, 2020.
[15]. J. Ali, N. Shati, M.T. Gaata, “Abnormal activity detection in surveillance video scenes”. TELKOMNIKA (Telecommunication Computing Electronics and Control), 18(5), 2447. https://doi.org/10.12928/TELKOMNIKA. V18I5.16634, 2020.
[16]. K. Pawar, V. Attar, V., “Deep learning approaches for video-based anomalous activity detection”, World Wide Web. doi:10.1007/s11280-018-0582-1