Skip to content

Smart Cart ML - Dataset and featuers preperation #199

Open
falah2001 wants to merge 6 commits intoDataBytes-Organisation:mainfrom
falah2001:Smart_Code_ML_Falah
Open

Smart Cart ML - Dataset and featuers preperation #199
falah2001 wants to merge 6 commits intoDataBytes-Organisation:mainfrom
falah2001:Smart_Code_ML_Falah

Conversation

@falah2001
Copy link
Contributor

Included files:

  1. User Creation
  • Generate synthetic user profiles (user_id, demographics, income, dietary preference, location).
  • Ensure realistic distribution (e.g., 30% health-conscious, 20% budget-focused).
  • Required: Null
  • Deliverable: users.csv.
  1. Transaction Simulation
  • Simulate shopping baskets influenced by preferences.
  • Randomized transaction dates across 3 year.
  • Assign transaction_id, user_id, product_code, transaction_date, transaction_price.
  • Required: Products.csv. Handled by other group member
  • Deliverable: transactions.csv.
  1. Behavioral & Product Relationships
  • Co-purchase analysis (products that appear together in baskets).
  • Behavioral metrics per user: Loyalty (repeat % with same product) and Switching tendency (category hopping).
  • Required: trans_with_promotions.csv. Handled by other group member
  • Deliverable: behavioral_relationships.csv.
  1. Visualization
  • Static charts (Seaborn/Matplotlib): histograms of spend, frequency.
  • Interactive dashboards (Plotly): Transactions by month (seasonality impact). Spend by demographic group. Co-purchase networks.
  • Required: trans.csv
  • Deliverable: Interactive dashboard notebook.

I developed the code for cleaning Coles data , selecting features for Smart Cart Model and generating synthetic data
Generate synthetic user profiles (user_id, demographics, income, dietary preference, location).
Ensure realistic distribution (e.g., 30% health-conscious, 20% budget-focused).
Simulate shopping baskets influenced by preferences.
Randomized transaction dates across 3 year.
Assign transaction_id, user_id, product_code, transaction_date, transaction_price.
Static charts (Seaborn/Matplotlib): histograms of spend, frequency.
Interactive dashboards (Plotly):
    Transactions by month (seasonality impact). Spend by demographic group. Co-purchase networks.
purchase analysis (products that appear together in baskets).
Behavioral metrics per user:
Loyalty (repeat % with same product).
Switching tendency (category hopping).
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant