Cognizant’s Artificial Intelligence and Data Analytics Practice provides advanced data collection and management expertise, as well as artificial intelligence and analytics capabilities that help clients create highly personalized digital experiences, products and services at every touchpoint of the customer journey.
During this program, i got the opportunity to step into the shoes of a Cognizant team member and complete tasks that replicate the work that our Artificial Intelligence team does every day. I learn how to perform exploratory data analysis, communicate results of a machine learning model, implement algorithm production, and review algorithm performance.
This repository contains the code and data for a predictive modeling project for Gala Groceries. The goal of the project is to build a model that can predict future sales of products at Gala Groceries stores.
The repository contains the following files:
- EDA/eda_kemal.ipynb: This Jupyter notebook performs exploratory data analysis on the sales data.
- Model Summary - Gala Groceries.pptx: This PowerPoint presentation summarizes the results of the modeling process.
- Model/modeling.ipynb: This Jupyter notebook builds and trains the predictive model.
- Model/modelling.py: This Python file contains the code for the predictive model.
- data/sales.csv: This CSV file contains the sales data for Gala Groceries stores.
- data/sensor_stock_levels.csv: This CSV file contains the sensor data for stock levels at Gala Groceries stores.
- data/sensor_storage_temperature.csv: This CSV file contains the sensor data for storage temperatures at Gala Groceries stores.
- email_task1.docx: This Word document contains the email task 1. Instructions To run the code in this repository, you will need to have the following installed:
Python 3.6+ Jupyter Notebook NumPy Pandas Matplotlib Scikit-learn Once you have installed the required software, you can clone the repository to your local machine:
git clone https://github.com/kemalmao19/cognizant.git
Then, open the Jupyter Notebooks in the EDA and Model directories and follow the instructions in the notebooks.
The results of the modeling process are summarized in the Model Summary - Gala Groceries.pptx presentation. The presentation shows that the predictive model was able to achieve a high accuracy on the test data.
If you have any questions about this repository, please contact me.