Scribd Logo
Upload

Welcome to Scribd!

  • 108 views

    Assignment 2 Problem

    Uploaded by

    Mohan Krishna
    Mr. Suresh, head of HR at Alvin Technologies, observed that 30-40% of candidates offered jobs eventually rejected them. Niraj, an employee in Alvin's HR analytics program, analyzed historical data of 7,000 candidates using machine learning to predict which variables affected joining and by what odds. His logistic regression model accurately predicted joins and non-joins. He then predicted which recently interviewed candidates were most likely to join based on the model.

    Copyright:

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

    Assignment 2 Problem

    Uploaded by

    Mohan Krishna
    108 views7 pages
    Mr. Suresh, head of HR at Alvin Technologies, observed that 30-40% of candidates offered jobs eventually rejected them. Niraj, an employee in Alvin's HR analytics program, analyzed historical data of 7,000 candidates using machine learning to predict which variables affected joining and by what odds. His logistic regression model accurately predicted joins and non-joins. He then predicted which recently interviewed candidates were most likely to join based on the model.

    Original Title

    Assignment 2 Problem (1)

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Mr. Suresh, head of HR at Alvin Technologies, observed that 30-40% of candidates offered jobs eventually rejected them. Niraj, an employee in Alvin's HR analytics program, analyzed historical data of 7,000 candidates using machine learning to predict which variables affected joining and by what odds. His logistic regression model accurately predicted joins and non-joins. He then predicted which recently interviewed candidates were most likely to join based on the model.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    108 views7 pages

    Assignment 2 Problem

    Uploaded by

    Mohan Krishna
    Mr. Suresh, head of HR at Alvin Technologies, observed that 30-40% of candidates offered jobs eventually rejected them. Niraj, an employee in Alvin's HR analytics program, analyzed historical data of 7,000 candidates using machine learning to predict which variables affected joining and by what odds. His logistic regression model accurately predicted joins and non-joins. He then predicted which recently interviewed candidates were most likely to join based on the model.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    of 7

    ASSIGNMENT 2: WORKFORCE ANALYTICS

    Alvin Technologies, a large software development and project management company located
    in Southern India recruits nearly 2000 engineers with specialization in Computer Sciences or
    Information Technology from the industry. Every year their need for manpower was on the
    rise. In the Indian software job market, number of engineers was more, but quality of most
    engineers was not up to the mark as set by the top management of Alvin Technologies.
    Hence, the recruitment screening process was conducted meticulously to identify the
    candidates with the right potential and after a rigorous five-round interview process, the best
    of the lot were extended offer letters.
    The HR Head of Alvin, Mr. Suresh KG observed that there was trend of roughly 30-40% of
    the candidates who were given joining offer to reject the same for better opportunities or
    reasons unknown. This was a serious worry for Mr. Suresh, since the cost and effort put in to
    zero down onto the final candidates was substantial. He was left pondering why so many
    individuals decide to not be part of Alvin, despite the firm taking care of major exigencies for
    the new joinees such as relocation expense coverage and flexible joining time to avoid notice
    period blues. Alvin was considered a good pay master and hence Mr. Suresh could not find
    any satisfactory explanation to this pattern. One of the junior staffs in the HR department
    -Mr. Niraj Babu approached the Head, HR and suggested that he may throw some light on the
    matter. Niraj has been enrolled in a HR Analytics certification course at a premier B School
    in India for past three months. This program was sponsored by Alvin, and Niraj felt obliged
    to help his department head with the pressing issue by sharing some analytic insights that he
    has picked up in his course. Niraj sought permission to get access to the existing data set of
    roughly 7000 employees who have appeared for interview till the offer letter stages for the
    firm in the past three years. He then first cleaned the existing data for any anomalies such as
    missing values and outliers. Finally, he fit the data in a ML model to understand the pattern
    behind the event of joining / not joining. Lastly, he applied the trained model on a data set of
    new candidates who were about to be extended offer letter by the firm.

    QUESTIONS

    1) Conduct a predictive analysis to test which of the independent variables are affecting the
    chance of joining for the candidates and by what odds with the Training data.
    2) Develop a ML model with the Training data using Logistic Regression to test the accuracy
    with which the outcome (joined / not joined) is getting predicted in terms of precision, recall,
    specificity and AUC.
    3) Predict which candidates are most likely to join based on the ML model with more
    accuracy as found using the fresh data (Test data) of recently interviewed candidates.
    Answer
    As we know if odds ratio is >1.1 then that variable is affecting the chance of joining.

    So here we can see

    Notice period has odds of 1.4 i.e., chances of candidate joining 1.4 times more if notice period is
    there

    Relocation required odds are 51.7 i.e., chances of candidate joining 51.7 times more if candidate is
    offered relocation

    Joining bonus odds are 0.62 <0.9 i.e., chances of candidate not joining 0.62 if joining bonus is given

    Rem factors have odds ratio between 0.9 & 1.1 so they can be omitted or can be concluded that they
    are not affecting candidates joining

    Joining Bonus

    Ans 2
    Confusion Matrix

    ROC Analysis

    Rank
    Test And score-
    Average

    Ans 3
    Prediction
    People most likely to join
    Most likely to not join

    There are high chances almost all will join except 22 people.

    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