DS_Association-Rules-on-Business-Problem
🥈SilverContext A real online retail transaction data set of two years. Content This is a transnational data set which contains all the transactions occurring between 01/12/2010 and 09/12/2011 for a UK-based and registered non-store online retail.The company mainly sells unique all-occasion gifts. Many customers of the company are wholesalers. Column Descriptors InvoiceNo: Invoice number. Nominal, a 6-digit integral number uniquely assigned to each transaction. If this code starts with letter 'c', it
300Updated 3mo ago
Intermediate30min to implementmarketing
Saves ~15 min per use
Quick InstallView Source
git clone https://github.com/mathchi/DS_Association-Rules-on-Business-Problem.gitWorks with:
Claude
Overview
About This Skill
This skill applies association rule mining to a real UK online retail dataset containing over two years of transactions from a non-store gift retailer. The dataset includes invoice details, product codes, quantities, pricing, and customer information across multiple countries, enabling analysis of which products are frequently purchased together. By mining association rules from this multivariate, time-series transaction data, marketing teams can uncover product relationships, optimize cross-selling strategies, and segment customers based on purchasing behavior. The skill supports RFM model-based customer segmentation and market analysis for precision marketing and business decision-making.
How to Use
["1. **Prepare the Dataset:** Ensure your transaction data includes columns for InvoiceNo, ProductID, Quantity, and CustomerID. Filter for wholesale customers using criteria like transaction frequency (>10/year) or order volume (>£1000/month).","2. **Run Association Rule Mining:** Use tools like Python's `mlxtend` library (Apriori algorithm) or Unique AI's built-in association rule module. Set minimum support=0.005, confidence=0.3, and lift threshold=2.0 to filter meaningful rules.","3. **Segment Results:** Separate rules by customer segments (e.g., wholesalers vs. retail) and time periods (e.g., holiday seasons). Exclude trivial associations (e.g., same product pairs) using a lift threshold >1.5.","4. **Validate Insights:** Cross-reference top rules with sales data to confirm lift values. For example, check if customers buying '6-COLOR PAINT SET' indeed purchase 'RED RETROSPOT CAKE CASES' at higher rates than average.","5. **Implement Actions:** Translate top rules into marketing campaigns (e.g., bundle discounts, email recommendations) and track performance using Unique AI's analytics dashboard. Monitor lift changes post-campaign to validate effectiveness."]
Use Cases
Identify frequently co-purchased products for cross-selling recommendations
Segment wholesale customers based on transaction patterns and order values
Analyze product affinity to optimize gift bundle offerings
Detect seasonal purchasing trends across the 24-month transaction history
Setup & Installation
Quick Install
No install command available. Check the GitHub repository for manual installation instructions.
Alternative Install (Git Clone)
git clone https://github.com/mathchi/DS_Association-Rules-on-Business-ProblemRequirements
- Claude Code or compatible AI agent
- Works with: Claude
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
Analyze the UK online retail transaction dataset ([DATASET_PATH]) using association rule mining to identify product affinities. Focus on wholesale customers (identified by [WHOLESALER_CRITERIA]) and transactions between [START_DATE] and [END_DATE]. Generate actionable insights for cross-selling opportunities by finding the top 5 product associations with the highest lift values. Exclude trivial associations (e.g., same product pairs) and format results as a ranked table with columns: Antecedent, Consequent, Support, Confidence, Lift, and Business Recommendation.
Example Output
### Association Rule Mining Results for Wholesale Customers (Dec 2010 - Dec 2011) **Top 5 Product Affinities by Lift Value:** | Antecedent Product | Consequent Product | Support | Confidence | Lift | Business Recommendation | |--------------------|--------------------|---------|------------|------|-------------------------| | **6-COLOR PAINT SET** | **SET/20 RED RETROSPOT CAKE CASES** | 0.012 | 0.45 | 3.8 | Bundle with cake cases for holiday promotions targeting event planners. | | **SET/20 RED RETROSPOT CAKE CASES** | **PLASTERS IN TIN WOODLAND** | 0.009 | 0.38 | 3.5 | Cross-sell woodland-themed party supplies with cake packaging. | | **JUMBO BAG RED RETROSPOT** | **60 TEATIME FAIRY CAKE CASES** | 0.011 | 0.42 | 3.2 | Promote fairy cake cases in jumbo bags for bulk purchases. | | **REGENCY CAKESTAND 3 TIER** | **PARTY BUNTING** | 0.008 | 0.35 | 2.9 | Upsell bunting with cake stands for themed party bundles. | | **SET/60 CAKE CASES ASSORTED** | **PAPER CHAIN KIT 50'S CHRISTMAS** | 0.007 | 0.33 | 2.7 | Seasonal bundle: assortment of cake cases + Christmas decorations. | **Key Insights:** - **Seasonal Patterns:** 78% of high-lift associations (Lift > 2.5) involve holiday-themed products (Christmas, Easter). Recommend creating themed gift bundles for Q4 (Oct-Dec). - **Wholesale Behavior:** 62% of associations involve bulk-packaged items (e.g., SET/20, SET/60), confirming wholesalers prefer volume discounts. - **Cross-Category Opportunities:** 40% of rules bridge different categories (e.g., cake cases → party supplies), suggesting untapped adjacency sales. **Actionable Next Steps:** 1. **Bundle Creation:** Design 3 holiday bundles combining top-associated products (e.g., 'Christmas Party Starter Kit' with cake cases, bunting, and fairy cakes). 2. **Wholesale Targeting:** Prioritize email campaigns for customers who purchased antecedent products in bulk (e.g., wholesalers buying 6-COLOR PAINT SET). 3. **Inventory Optimization:** Stock 20% more of consequent products (e.g., RED RETROSPOT CAKE CASES) during peak seasons to meet demand from antecedent purchases. 4. **A/B Testing:** Test bundle discounts vs. free shipping on consequent products to measure incremental revenue per rule. *Dataset: 541,909 transactions | Wholesale Filter: Customers with >10 transactions/year | Date Range: 01/12/2010 - 09/12/2011*
Apply to these tools
Browse all toolsUnique
Enterprise AI for Finance
Descript
AI video and podcast editing
Namaste Business
Shopify for a mobile-first world
InsightData Business Intelligence Apps
Zie zelf welke beslissingen vandaag in je data verborgen zitten
Microsoft Dynamics 365 Business Central
A comprehensive ERP solution to enhance business efficiency
Smart Business Manager
AI-powered platform for managing customers, workflows, and business operations
Compatible MCP servers
Browse all MCP serversFind the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan