- 25th August, 2020.
- Repository created.
- 26th August, 2020.
- Understanding the problem statement.
- Explored the data.
- ReadME.md file created.
- 27th August, 2020.
- Distributing the work among the team members.
- Issues created.
- Data Analysed.
- Repositories forked and pull request created for variable identification.
- 28th August, 2020.
- Data imported.
- Data cleaning started.
- Landing page of our website created.
- 29th August, 2020.
- Data cleaning completed.
- Start Exploratory Data Analysis.
- 30th August, 2020.
- Exploratory Data Analysis completed.
- Creation of Input page begun.
- 31st August, 2020.
- Tried to merge the data into one pipeline.
- Eliminated redundant features from the dataset.
- 1st September, 2020.
- Merging all the useful features in one dataframe.
- Algorithm for the model was decided.
- 2nd September, 2020.
- Input page creation completed.
- Added an encoded columns to the merged columns.
- 3rd September, 2020.
- Model building started.
- Importance of individual features calculated.
- 4th September, 2020.
- Models split into two.
- Input page changed.
- One model created.
- 5th September, 2020.
- Second model creaed.
- Enhancement of model 1.
- Enhancement of model 2.
- 6th September, 2020.
- Models built successfully.
- Landing page hosted using Flask.
- 7th September, 2020.
- Models saved in Pickle files.
The data simulates how people make purchasing decisions and how those decisions are influenced by promotional offers. Each person in the simulation has some hidden traits that influence their purchasing patterns and are associated with their observable traits. People produce various events, including receiving offers, opening offers, and making purchases. As a simplification, there are no explicit products to track. Only the amounts of each transaction or offer are recorded. There are three types of offers that can be sent: buy-one-get-one (BOGO), discount, and informational. In a BOGO offer, a user needs to spend a certain amount to get a reward equal to that threshold amount. In a discount, a user gains a reward equal to a fraction of the amount spent. In an informational offer, there is no reward, but neither is there a requisite amount that the user is expected to spend. Offers can be delivered via multiple channels. This was a prompt description about the data and the scenario on which we will be working on.
We aim to create a web-app which will be used to predict the best possible offer that would attract a customer on the basis of his description. We also aim at delivering certain graphs which will help us understand the purchasing patterns of the customers.
- ⛳ Data Science
- Data cleaning and pipelining
- Exploratory Data Analysis
- Building a model
- Training the model
- Testing the model
- Improvising the model
- Saving the model in a pickle file extension
- ⛳ Creation of API
- Importing the Pickle file
- Run FLask and request predictions
- Testing the API
- ⛳ Web Development
- Front End
- Landing page
- Input Form
- Visualization of graphical data
- Back End
- Integrating the API with the web-app
- Calling of responses for the input.
- Front End
Finally, we will be hosting the website where the owner of the shop will provide the needful information. Consequetly, we will display the graphical representation of the purchasing pattern of that particular customer and recommend the type of offer to be sent in order to optimize the sales.