Multi-Strategy Algorithms

In Multi-Strategy Algorithms, more than one algorithm performs to offer a related product recommendation to users. The algorithms covered under Multi-Strategy Algorithms are:

• Mixed Strategy
• Chef

Mixed Strategy

A mixed strategy involves employing various algorithms for different slots within the Recommendation Widget. This approach enables the simultaneous use of multiple algorithms within a single recommendation widget on your website.

• Page Type: All Pages, Product/Article Pages, Category Pages, Cart Page
• Example Use Case: Promoting products provided from a different range of Smart Recommender algorithms.
• Fallbacks: Complicated - Each slot's fallback is given 
• Prerequisites: Depends on the selected algorithms.
• Maximum Number of Products to Recommend (in the same variant): 15 

Chef

Chef, the automated recommendation algorithm, dynamically determines the optimal mixed strategy combination by assessing algorithms such as the most popular items, top sellers, user-based, highest discounted, new arrivals, and trending items. This iterative testing process aims to enhance conversion rates and deliver the most effective recommendations.

• Page Type: Home page
• Example Use Case: Taking into account the most popular items, top sellers, user-based, highest discounted, new arrivals, and trending items algorithms, the Chef evaluates recommendations of each algorithm one by one by calculating the precision of each slot and eventually recommending products with the highest precision. 
• Fallbacks: Complicated - Each slot's fallback is given 
• Prerequisites: 
  • It evaluates the most popular items, top sellers, user-based, highest discounted, new arrivals, and trending items algorithms, whichever is enabled for your account. If only 3 of those are activated, then Chef creates its combination based on those 3 open algorithms.
  • Chef works with 60 days of data. This is why we highly recommend you have Smart Recommender open for at least 2 months for better results. 
  • Chef also works for new accounts (with data less than 60 days) by providing a default strategy that is derived based on best practices. However, its results will get better once more data is collected for you.
• Maximum Number of Products to Recommend (in the same variant): 15