en

Personalized Recommendation

Goals

  • Reduce user effort required to find products of interest
  • Maximize revenue while optimizing conversion rates by presenting the offers most attractive to each user
  • Develop the capacity to recommend products without a sales history and modify the recommendation based on available stock

Data

  • User profiles
  • Purchase history
  • Browsing history
  • Abandoned carts
  • Newsletter clicks
  • Campaign responses
  • Product taxonomy

Analytics

  • Affinity analysis
  • Offer diversification
  • No repeat of already viewed offers
  • Prioritization of new products
  • Algorithms with high parallelization

Business

  • Integration with mailing and web tools
  • System operation in accordance with KPI’s (conversion, revenue, margin)
  • Recommendations for users with no purchase history
  • Ability to include expert rules

Results

  • Increase in net margin between 5% and 20% for the online channel according to customer and sector
  • Increased sales in the off-line channel for retailers with a network of retail outlets
  • Self-learning algorithms for continuous improvement

This site uses cookies to ensure the best user experience. By continuing to navigate you are giving your consent to cookies being used according to our cookie policy.
Click the link for more information.