INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Taxi service is a very important part of public transportation in advanced cities, providing convenience for our lifestyle. Taxi services in trendy cities' area units are typically corrupted by fraud, and passenger area units are overcharged by taxi drivers. Existing trip detection models believe the idea that the trip is properly recorded by the meter. However, there is a unit of several taxi drivers in Asian nations carrying passengers while not activating the meter, particularly once the taxi driver is attempting to overcharge the passengers. Thus, the present system predicts the unmetered taxi trips area unit detected in real-world situations, which describes the taxi trip that has been recorded as vacant but has similar driving behaviors to regular metered trips. It consists of a learning model that predicts the occupancy standing of taxis, but the prediction level is deficient, and it is not correct. This paper proposes the K-Nearest Neighbour (KNN) machine learning algorithmic rule to determine tax fraud. Taxi fraud is determined by the cost per kilometer, if the driver overcharges the passenger the model predicts the fraud. In this model, first, the dataset has been trained for fraud detection. Second, the cost for the taxi trip is calculated based on the one-way, round trip, and including waiting time. Experimental results reveal that the proposed model detects taxi driver fraud within the calculation of trip sheets and enhances accuracy in identifying overcharging in fraud detection.
"Fiddle Tour Fraudulent Taxi Trip Detection using KNN Machine Learning Algorithm", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.9, Issue 1, page no.c447-c465, January-2024, Available :http://www.ijnrd.org/papers/IJNRD2401260.pdf
Downloads:
000118797
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn