BIG MART SALES PREDICTION AND

ANALYSIS

PRESENTED BY: Guided By:

SOMISETTY PAVAN KUMAR(200303124474) ADITI MISHRA
THUMMAPUDI BALA SAI VIVEK(200303124502)
CSE Department
YARRAMSETTI JAYA SAI SUNNY(200303124546)
PIET, Parul University
VURA VAMSI SRINIVAS(200303124539)
 02/02/24

CONTENT
• Introduction
• Problem Statement
• Research Paper Summary in Table form
• Flowchart of the system
• Implementation Details
• Screen shots of implemented work
• Demonstration of the Project
• Conclusion
• Future Work
• References
 02/02/24

INTRODUCTION
• In Today’s World Big malls and marts records sales data of individual items for predicting future demand and
inventory management.
• This data stores a large number of attributes of the item as well as individual customer data together in a data
warehouse.
• The number of malls and stores are increasing day by day so there is huge competition in between them
regarding their sales.
• Each of them are trying to attract more customers using personalized and short time offers which makes the
prediction of future volume of sales of every product.
• Due to cheap availability of computing and storage , it has become very easy to use efficient Machine learning
algorithms for this purpose.
PROBLEM STATEMENT

•Big Mart is a large retail chain with multiple stores spread across different locations. The company
collects vast amounts of data regarding sales transactions, store attributes, and product information.
• The objective of this project is to develop a machine learning model that can accurately predict the
sales of Big Mart stores based on various features.
•The model should provide insightful analysis and recommendations to optimize sales performance.
 SUMMARY
Sr. Paper Title Publisher Year Take-away points
number

1. Data Preprocessing Techniques International Journal of 2018 Pre-Processing of Dataset.

for Machine Learning Computer Science and
Information Security
2. Handling Missing Values in International Journal of 2017 How to handle missing values using
Data Preprocessing for Machine Computer Applications various imputation techniques and
Learning statistical methods
3. Handling Missing Data in International Journal of 2017 Knowing about the implementation of
Machine Learning: A Survey on Advanced Research in various techniques for handling
Different Techniques and Their Computer Science missing data.
Impact
4. Sales Prediction in Retail International Journal of 2018 Knowing about various sales
Industry using Machine Computer Applications prediction models in the Industry.
Learning Algorithms
5. Sales Forecasting in Retail: A IEEE Xplore 2020 How can we predict sales using
Comparative Study of Machine various machine learning models.
Learning Approaches
FLOWCHART OF THE SYSTEM
IMPLEMENTATION DETAILS

• We will import all the necessary modules like numpy , pandas ,matplotlib , and sklearn.
• After the importation of modules is done we will the dataset into the google colab.
• We will find how many features and data points are there in the dataset.
• Next we will know about the data set by using the .info() method in python.
• The .info() method is a method in pandas library which is used for knowing the datatype of each
column and it will tell how many non null values are present in each column along with the type of
column whether its null or not null.
• After Knowing about the dataset we will move to the next step which is handling with missing
values.
• We will find the count of missing values in the dataset using the .isnull().sum() function.
• After Knowing the count of missing values in each column we will replace the missing
values of each column with the mean or mode of that column.
• Whether if the column contains integer or floating point data type we will replace with
the mean value of that column
• If the data contains string like data we will replace it with the mode of that column.
• For calculating mean and mode in python we use .mean() and .mode() in-built functions
in python.
• Next we will the categorical features and numerical features in the dataset.
SCREEN SHOTS OF IMPLEMENTED WORK

• Import of Modules
• Loading the dataset.
• Info of the Dataset
• Finding the Number of Missing Values
• Finding the Mean Of Item weight column and replacing null values with it.
• Finding the mode of Outlet size column and replacing it with null values.
CONCLUSION
• BigMart sales prediction and analysis using machine learning can offer valuable insights
and help optimize business strategies.
• By Predicting the Sales the industry can know the details about their sales and which
store is having how much sales and they can manage the inventory with the items that are
having huge amount of sales.
• With the help of Machine learning algorithms it has became easy to identify the hidden
patterns of the data.
FUTURE WORK

• In future we will find the hidden patterns of the data using various visualisation tools like
matplotlib and seaborn.
• After finding the hidden patterns of the data we will split the dataset for training and
testing.
• We will train the model using the training dataset and after the training is done we will
test the model.
• Finally we will check the Accuracy of the Model.
 REFERENCES

• “Data Preprocessing Techniques for Machine Learning" by B. Bhattacharya and S. Das, International Journal of Computer Science and
Information Security, 25th January 2018.
• “Handling Missing Values in Data Preprocessing for Machine Learning" by V. Verma and S. Maheshwari , International Journal of Computer
Applications, 6th April 2017.
• "Handling Missing Data in Machine Learning: A Survey on Different Techniques and Their Impact" by A. Sharma and S. Sharma, International
Journal of Advanced Research in Computer Science, 20th September 2017.
• "Sales Prediction in Retail Industry using Machine Learning Algorithms" by A. Bhardwaj, A. Singla, and M. R. Gupta, International Journal of
Computer Applications, 16th March 2018.
• "Sales Forecasting in Retail: A Comparative Study of Machine Learning Approaches" by A. Khaki, P. S. Singh, and R. P. Singh, IEEE Xplore,
5th July 2020.
THANK YOU