Scribd Logo
Upload

Welcome to Scribd!

  • 143 views

    Predicting Fraudulant Job Ads With Machine Learning

    Uploaded by

    IJARSCT Journal
    This document discusses predicting fraudulent job ads with machine learning. It evaluates various classifiers like passive aggressive, naive bayes, random forest and their ability to detect fake job posts. Passive aggressive and naive bayes classifiers achieved the highest accuracy rates of 98.12% and 96.72% respectively.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Predicting Fraudulant Job Ads With Machine Learning

    Uploaded by

    IJARSCT Journal
    143 views3 pages
    This document discusses predicting fraudulent job ads with machine learning. It evaluates various classifiers like passive aggressive, naive bayes, random forest and their ability to detect fake job posts. Passive aggressive and naive bayes classifiers achieved the highest accuracy rates of 98.12% and 96.72% respectively.

    Original Description:

    Predicting Fraudulant Job Ads with Machine Learning

    Original Title

    Predicting Fraudulant Job Ads with Machine Learning

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses predicting fraudulent job ads with machine learning. It evaluates various classifiers like passive aggressive, naive bayes, random forest and their ability to detect fake job posts. Passive aggressive and naive bayes classifiers achieved the highest accuracy rates of 98.12% and 96.72% respectively.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    143 views3 pages

    Predicting Fraudulant Job Ads With Machine Learning

    Uploaded by

    IJARSCT Journal
    This document discusses predicting fraudulent job ads with machine learning. It evaluates various classifiers like passive aggressive, naive bayes, random forest and their ability to detect fake job posts. Passive aggressive and naive bayes classifiers achieved the highest accuracy rates of 98.12% and 96.72% respectively.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 3

    ISSN (Online) 2581-9429

    IJARSCT
    International Journal of Advanced Research in Science, Communication and Technology (IJARSCT)

    Volume 3, Issue 2, April 2023


    Impact Factor: 7.301

    Predicting Fraudulant Job Ads with Machine


    Learning
    Hitesh Ahire1, Aashish Kumar Singh2, Arpit Bhorkar3, Shrushti Daware4, Prof. P. A. Deole5
    Students, Department of Computer Engineering1,2,3,4
    Assistant Professor, Department of Computer Engineering5
    Smt. Kashibai Navale College of Engineering, Pune, Maharashtra, India

    Abstract: Online Recruitment frauds are becoming an important issue in cyber-crime region. Companies
    find it easier to hire people with the help of the internet rather than the old traditional way. But it has
    greatly attracted scammers. In this project, we have proposed a solution on how to detect ORF. We have
    presented our results based on the previous model and the methodologies, to create the ORF detection
    model where we have used Jobs_Frauds.csv . We have selected this dataset from Kaggle . Furthermore,
    Dummy Classifier, Random Forest Classifier, Support Vector Machine, Gradient Boosting, Naïve Bayes
    Classifiers, XG Boost, SGD classifier, Passive Aggressive and KNN are the algorithms that have been used.
    We have found the accuracy of different prediction models, where Passive Aggressive (98.12%) and
    Gaussian Naïve Bayes (96.72%) give the highest accuracy. Through this project, we tried to create a
    precise way for detecting fraudulent hiring posts.

    Keywords: Passive Aggressive, Naïve Bayes, SVM , Job Ads.

    I. INTRODUCTION
    Most modern organizations use the web and social media platforms for employee recruitment and job opening
    advertisements. Online job posts are easily accessed by interested job-seekers. Unfortunately, this trend creates an
    opportunity for criminals to exploit job seekers with fake job offers.
    The Job advertisement and recruitment process has been improved by using online advertisements. These ads are being
    used by criminals as a means of committing fraud. A system that can automatically identify fake job ads using their
    attributes will reduce the chances of job seekers falling a victim to scams. This project aims to develop a machine
    learning classifier to flag fake and real job advertisements

    II. PROBLEM STATEMENT


    To avoid fraudulent post for job in the internet, an automated tool using machine learning based classification
    techniques is proposed in the paper. Different classifiers are used for checking fraudulent post in the web and the results
    of those classifiers are compared for identifying the best employment scam detection model. It helps in detecting fake
    job posts from an enormous number of posts. Two major types of classifiers, such as gradient boost and naïve bayes
    classifiers are considered for fraudulent job posts detection. However, experimental results indicate that naïve bayes
    and gradient boost classifiers are the best classification to detect scams over other classifiers.

    III. MOTIVATION
     Most modern organisations use the web and social media platforms for employee recruitment and job opening
    advertisements.
     Online job posts are easily accessed by interested job-seekers, hence its popularity.
     Unfortunately, this trend creates an opportunity for criminals to exploit job seekers with fake job offers.
     Criminals extract personal information to be used in nefarious activities.

    Copyright to IJARSCT DOI: 10.48175/IJARSCT-9123 238


    www.ijarsct.co.in
    ISSN (Online) 2581-9429
    IJARSCT
    International Journal of Advanced Research in Science,, Communication and Technology (IJARSCT)

    Volume 3, Issue 2, April 2023


    Impact Factor: 7.301

    IV. SYSTEM REQUIREMENTS


    4.1 Hardware Requirements:
     Processor : Intel i3 minimum or more
     Disk Space : At least 3GB for Python IDE
     RAM : 4GB minimum or more

    4.2 Software Requirements


     Python IDE
     Stremlit (online tool for Deployment)

    V. METHODOLOGY
    Module l - (Ads acquisition)
     We are going to use dataset from Kaggle for classification.
     Jobs will be taken from external source or online.
     Currently we are going to take a dataset around 17880 jobs from an open source dataset platform(Kaggle).

    Module 2 - (Preprocessing )
     The dataset was made up of features with a lot of null values and some with little or nno null values. A 60%
    threshold for null was used to identify the columns that were dropped from the dataset.
     Null values were imputed with empty strings.
    Use Case:

    Sequence Diagram

    Copyright to IJARSCT DOI: 10.48175/IJARSCT-9123 239


    www.ijarsct.co.in
    ISSN (Online) 2581-9429
    IJARSCT
    International Journal of Advanced Research in Science, Communication and Technology (IJARSCT)

    Volume 3, Issue 2, April 2023


    Impact Factor: 7.301

    Proposed System:
    Algorithms used:
     Dummy Classifier
     Random Forest
     SVC
     Gaussian Naïve Bayes
     Passive Aggressive

    VI. CONCLUSION
    In our research we have compared the performance of different machine learning algorithms like Dummy Classifier,
    Random Forest Classifier, Support Vector Machine, Gradient Boosting, Naïve Bayes Classifiers, XG Boost, SGD
    classifier, Passive Aggressive and KNN and determined which algorithm works best on our dataset. We did not only
    use the most common algorithms but also some latest ones so that we can determine how well do they work. We have
    seen that range of accuracy of all our algorithms lie between 96% to 98%. The main purpose for our model is to help
    the job seekers identify which jobs are fake and save themselves from fraudsters. Our model can also be used by
    different online job recruitment sites to detect fraudulent jobs. We have identified that some features play an important
    role in determining whether a job is fake or not. In future, we plan to incorporate these features in our dataset and thus
    try to further increase the accuracy range of the algorithms.

    REFERENCES
    [1]. Ibrahim M. Nasser; Amjad H. Alzaanin; Ashraf Yunis Maghari, Online Recruitment Fraud Detection using
    ANN, 2021
    [2]. Hridita Tabassum; Gitanjali Ghosh; Afra Atika; Amitabha Chakrabarty, Detecting Online Recruitment Fraud
    Using Machine Learning,2021
    [3]. Sangeeta Lal; Rishabh Jiaswal; Neetu Sardana; Ayushi Verma; Amanpreet Kaur; Rahul Mourya,
    ORFDetector: Ensemble Learning Based Online Recruitment Fraud Detection, 2019
    [4]. Asad Mehboob & M. S. I. Malik, Smart Fraud Detection Framework for Job Recruitments, 2020
    [5]. Bandar Alghamdi, Fahad Alharby, An Intelligent Model for Online Recruitment Fraud Detection, 2019

    Copyright to IJARSCT DOI: 10.48175/IJARSCT-9123 240


    www.ijarsct.co.in

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy