Big-Mart-Sales-Prediction

Using Regression Analysis

Introduction

Practice problems or data science projects are one of the best ways to learn data science. You don’t learn data science until you start working on problems yourself.

BigMart Sales Prediction practice problem was launched about a month back, and 624 data scientists have already registered with 77 among those making submissions. If you’re finding it difficult to start or if you feel stuck somewhere, this article is meant just for you. Today I am going to take you through the entire journey of getting started with this data set.

I hope that this article will help more and more people start their data science journey!

Hypothesis Generation:

understanding the problem better by brainstorming possible factors that can impact the outcome

Data Exploration:

looking at categorical and continuous feature summaries and making inferences about the data.

Data Cleaning:

imputing missing values in the data and checking for outliers

Feature Engineering:

modifying existing variables and creating new ones for analysis

Model Building:

making predictive models on the data

Store Level Hypotheses:

City type:

Stores located in urban or Tier 1 cities should have higher sales because of the higher income levels of people there.

Population Density:

Stores located in densely populated areas should have higher sales because of more demand.

Store Capacity:

Stores which are very big in size should have higher sales as they act like one-stop-shops and people would prefer getting               everything from one place

Competitors:

Stores having similar establishments nearby should have less sales because of more competition.
Marketing: Stores which have a good marketing division should have higher sales as it will be able to attract customers through the     right offers and advertising.

Location:

Stores located within popular marketplaces should have higher sales because of better access to customers.

Customer Behavior:

Stores keeping the right set of products to meet the local needs of customers will have higher sales.

Ambiance:

Stores which are well-maintained and managed by polite and humble people are expected to have higher footfall and thus higher sales.
Product Level Hypotheses:

Product Level Hypotheses:

Brand:

Branded products should have higher sales because of higher trust in the customer.

Packaging:

Products with good packaging can attract customers and sell more.

Utility:

Daily use products should have a higher tendency to sell as compared to the specific use products.

Display Area:

Products which are given bigger shelves in the store are likely to catch attention first and sell more.

Visibility in Store:

The location of product in a store will impact sales. Ones which are right at entrance will catch the eye of customer first rather       than the ones in back.

Advertising:

Better advertising of products in the store will should higher sales in most cases.

Promotional Offers:

Products accompanied with attractive offers and discounts will sell more.

adil-imran / big-mart-sales-prediction Goto Github PK