Real-Time Cross-Selling Proposal Calculation
A method for generating cross-selling product recommendations is provided. The method includes determining one or more base products purchased by a selected customer based on billing data, finding other customers who purchased the base products, determining one or more additional products which have been purchased by the other customers, sorting the additional products, and providing predictive data including information relating to the additional products to be recommended to the selected customer. Related apparatus, systems, techniques and articles are also described.
1 . A computer-implemented method, comprising:
determining one or more base products purchased by a selected customer based on billing data stored in a database;
finding, in the database, one or more other customers who purchased the one or more base products;
determining one or more additional products which have been purchased by the one or more other customers;
sorting the one or more additional products by revenue and selecting one or more top additional products based on revenue;
providing predictive data comprising information relating to the one or more top additional products to be recommended to the selected customer;
wherein at least one of the above is a set-oriented process performed on at least one processor.
2 . The computer-implemented method according to claim 1 , further comprising determining a revenue ratio between the revenue of each one or more base products and each one or more top additional products.
3 . The computer-implemented method according to claim 1 , wherein the predictive data is provided in real-time based on real-time billing data.
4 . The computer-implemented method according to claim 1 , further comprising determining a buying probability of each one or more top additional products.
5 . The computer-implemented method according to claim 1 , further comprising determining an expected revenue for each one or more top additional products.
6 . The computer-implemented method according to claim 1 , further comprising determining an expected margin for each one or more top additional products.
7 . The computer-implemented method according to claim 1 , wherein the database utilizes in-memory technology.
8 . A computer program product comprising a non-transitory machine-readable medium storing instructions that, when executed by at least one programmable processor, cause the at least one programmable processor to perform operations comprising:
determining one or more base products purchased by a selected customer based on billing data stored in a database;
finding, in the database, one or more other customers who purchased the one or more base products;
determining one or more additional products which have been purchased by the one or more other customers;
sorting the one or more additional products by revenue and selecting one or more top additional products based on revenue; and
providing predictive data comprising information relating to the one or more top additional products to be recommended to the selected customer.
9 . The computer program product according to claim 8 , further comprising determining a revenue ratio between the revenue of each one or more base products and each one or more top additional products.
10 . The computer program product according to claim 8 , wherein the predictive data is provided in real-time based on real-time billing data.
11 . The computer program product according to claim 8 , further comprising determining a buying probability of each one or more top additional products.
12 . The computer program product according to claim 8 , further comprising determining an expected revenue for each one or more top additional products.
13 . The computer program product according to claim 8 , further comprising determining an expected margin for each one or more top additional products.
14 . The computer program product according to claim 8 , wherein the database utilizes in-memory technology.
15 . A system comprising:
at least one programmable processor; and
a non-transitory machine-readable medium storing instructions that, when executed by the at least one programmable processor, cause the at least one programmable processor to perform operations comprising:
determining one or more base products purchased by a selected customer based on billing data stored in a database;
finding, in the database, one or more other customers who purchased the one or more base products;
determining one or more additional products which have been purchased by the one or more other customers;
sorting the one or more additional products by revenue and selecting one or more top additional products based on revenue; and
providing predictive data comprising information relating to the one or more top additional products to be recommended to the selected customer.
16 . The system according to claim 15 , wherein the operations further comprises determining a revenue ratio between the revenue of each one or more base products and each one or more top additional products.
17 . The system according to claim 15 , wherein the predictive data is provided in real-time based on real-time billing data.
18 . The system according to claim 15 , wherein the operations further comprises determining a buying probability of each one or more top additional products.
19 . The system according to claim 15 , wherein the operations further comprises determining an expected revenue for each one or more top additional products.
20 . The system according to claim 15 , wherein the operations further comprises determining an expected margin for each one or more top additional products.