recommendo enables increased sales!

recommendo, commendo's recommendation engine, optimizes the product recommendations of your online shop on the basis of individual shopping attitudes and user characteristics.

Find here: technical features and integration

Increasing revenue

Optimization of individual product recommendations happens in real-time and continually, typically resulting in sales increases of up to 20%.

Customer loyalty

recommendo bases its personalized recommendations on the individual shopping behavior of each customer. Results typically include:
  • increased customer satisfaction
  • stronger customer loyalty
  • more time spent shopping online at the client's site

Improving sales

recommendo provides personalized recommendations for all the client‘s products, as well as applicable statistical similarities between products. Thus, similar products and recommendations, which meet the individual customer's taste, are shown to him or her online. The results include:
  • imporoved product promotion
  • custom-fit recommendations that lead to impulse buying
  • sales increase that lead to increased revenue

Integration and autonomy

Knowing each individual customer's taste is the basis of an online retailer‘s success. recommendo was developed for the special demands of online marketers. Since it is an independent closed system, it can easily be integrated in distribution portals. recommendo is a stand alone software product that is easily integrated as auxiliary module into the structure of your online shop. The benefits of that include:
  • no privacy issues
  • no outer data circulation

Leading technology

A hybrid personalized recommendation engine provides a bridge over the so called coldstart problem by switching intelligently between collaborative filtering algorithms and content based filtering techniques.
  • collaborative filtering
  • content based filtering

recommendo compared to conventional cross selling

 real time learning  YES no
 increased revenue via cross selling  YES  YES
 increased revenue via up selling  YES no
 providing recommendations based on large shopping carts  YES  YES
 providing recommendations based on small shopping carts
 (from first purchase on)
 YES no
 providing recommendations based on rarely sold products
 (niche products)
 YES no
 providing recommendations of recent products  YES no
 avoiding top seller recommendations only  YES no
 most effective recommendations due to leading technology  YES no
 user-item precitions & item-item correlations  YES no
 no drawback to performance due to optimized speed  YES no
 compatible recommendations  YES no