The problem Market Basket Analysis solves

Our market basket analysis project, developed during DataHack 1.0, comprises three Jupyter Notebooks for streamlined analysis. "DataHack_PreProcessing.ipynb" focuses on data preparation, addressing missing values, negative entries, and unnecessary columns through meticulous preprocessing, including label encoding for relevant data.

"Datahack_FeatureSelection.ipynb" introduces clustering for the "order_id" column, grouping similar items ordered by customers, enhancing the dataset's analytical depth.

In "Datahack_Model.ipynb," we harness the Apriori algorithm for data mining, identifying frequent itemsets for predictive insights based on user input, laying the foundation for strategic decision-making.

Use Cases:

Menu Optimization: Identify frequently ordered item combinations for strategic menu curation.
Recommendation System: Implement a ChatBot using collaborative filtering to suggest items based on customer preferences.
Website Integration: Showcase restaurant information on a static website, seamlessly incorporating the ChatBot for enhanced user interaction.

Challenges I ran into

Challenges Overcome:

A specific challenge involved handling missing values and negative entries during preprocessing. Iterative data cleaning and validation processes were implemented in "DataHack_PreProcessing.ipynb" to ensure data integrity and reliability.