AV Internship Hiring EDA Assignment
About the Event
If you have the ability to think in a structured and streamlined manner, love working on strategy can simplify complex concepts, and are interested in developing next-gen data science learning content, we have a role for you. But first, you need to prove that you have what it takes.
What is the task?
You are given a real-world problem along with the dataset. The problem is related to HR analytics. The task is to predict whether an employee will be nominated for promotion or not. The dependent/target variable here is is_promoted. You have to explore the dataset and find insights from it.
Data
You can download the dataset from here.Dataset Description
Here is a brief summary of what is required as a part of this assignment:
1. Univariate Analysis
Analyse the variables individually and find out patterns in them.
2. Bivariate Analysis:
2.1 Independent and independent variable
Find the relationship between independent variables. How independent variables are related to each other.
2.2 Independent and dependent variable
Find the relationship between dependent and independent variables. Bring out interesting insights from the data and point out the variables that could be useful while creating machine learning models.
How much time do you have to complete this task?
3 days
What is the Mode of Delivery?
You have to submit the code file (Jupyter Notebook) using the solution checker.
NOTE: You can make as many submissions as you want. We will consider your last submission as the final submission for evaluation.
Guidelines you should follow during exploration
- Only use Python for all the exploration
- First create an outline of your exploration process and then implement each step in Python
- Visualisations are a great way to get attention. Use them wisely to bring out the most important insights
- The structure of your exploration matters the most. Make sure the notebook has essential comments and is readable as a data story.
Participate in Discussion
Registration Details
Total registered
Know where you stand
Spaces You Can Join
Frequently Asked Questions
Find the answers for the most frequently asked questions
Participants benefit from one-on-one feedback, publication on a respected platform, recognition from a global audience, and monetary rewards for each published article. Additionally, the top articles receive special rewards.
Each article must be original, and pass plagiarism and not AI generated content checks. You can submit multiple articles as long as each is distinct. Proper citation of all references and image sources is mandatory.
There are no specific requirements to register for the hackathon, although it is recommended to have some basic knowledge of the relevant topics, such as Data Science, Machine Learning, or Deep Learning, along with proficiency in a coding language, preferably Python.
In the Blogathon, an article typically explores a specific topic or idea within Data Science or Generative AI and is required to be at least 1000 words long. A guide, on the other hand, is a more comprehensive resource, covering all aspects of a particular subject in data science, and must be at least 2500 words long. Guides aim to serve as a one-stop resource, providing detailed insights and practical applications, whereas articles might focus on narrower or more specific topics.
Depending on the type of competition, you can participate individually or in a team.
Multiple submissions of the same article are prohibited and could lead to disqualification. Articles failing to meet the required length, originality, or citation standards will be rejected.
AVCC is a community for authors who have had three or more articles published in the Blogathons. Members benefit from monetary rewards for each published article and get the opportunity to showcase their work to a larger audience.
You can access the problem statement under the "Problem Statement" tab once the Hackathon is live.
Please login/signup to participate in the discussion
0/1000