Account recommendations for user account sets
New account recommendations for user account sets are described. A system creates an accounts profile for a set of accounts based on multiple attributes associated with each account of the set of accounts. The system calculates an account score for an account based on comparing multiple attributes associated with the account against the accounts profile, wherein the account is not in the set of accounts. The system determines whether the account score satisfies an account score threshold. The system recommends the account to a user associated with the set of accounts if the account score satisfies the account score threshold.
1. A system for new account recommendations for user account sets, the system comprising:
one or more processors; and
a non-transitory computer readable medium storing a plurality of instructions, which when executed, cause the one or more processors to:
train a machine-learning system to build an accounts profile model for a plurality of existing customer sales accounts which are a sales responsibility of a user, based on a plurality of firmographic attributes associated with each account of the plurality of existing customer sales accounts;
determine an account similarity score for a prospective customer sales account based on comparing a plurality of firmographic attributes associated with the prospective customer sales account against the accounts profile model, wherein the plurality of existing customer sales accounts excludes the prospective customer sales account;
determine whether the account similarity score satisfies an account score threshold; and
recommend for the user, who is responsible for the plurality of existing customer sales accounts for which the accounts profile model was built, to take sales responsibility for the prospective customer sales account, in response to a determination that the account similarity score satisfies the account score threshold.
2. The system of claim 1 , wherein training the machine-learning system to build the accounts profile model for the plurality of existing customer sales accounts is further based on recency-weighting each existing customer sales account of the plurality of existing customer sales accounts.
3. The system of claim 1 , wherein training the machine-learning system to build the accounts profile model for the plurality of existing customer sales accounts comprises accommodating a missing attribute value in the plurality of existing customer sales accounts.
4. The system of claim 1 , wherein training the machine-learning system to build the accounts profile model for the plurality of existing customer sales accounts is further based on a user provided attribute preference.
5. The system of claim 1 , wherein the plurality of existing customer sales accounts is further associated with at least one of a plurality of users and a random sampling of existing customer sales accounts.
6. The system of claim 1 , wherein training the machine-learning system to build the accounts profile model for the plurality of existing customer sales accounts comprises adjusting for an attribute dependency in the plurality of existing customer sales accounts.
7. The system of claim 1 , wherein training the machine-learning system to build the accounts profile model for the plurality of existing customer sales accounts is further based on at least one user success attribute associated with each existing customer sales account of the plurality of existing customer sales accounts.
8. A computer program product comprising computer-readable program code to be executed by one or more processors when retrieved from a non-transitory computer-readable medium, the program code including instructions to:
train, by a database system, a machine-learning system to build an accounts profile model for a plurality of existing customer sales accounts which are a sales responsibility of a user, based on a plurality of firmographic attributes associated with each account of the plurality of existing customer sales accounts;
determine, by the database system, an account similarity score for a prospective customer sales account based on comparing a plurality of firmographic attributes associated with the prospective customer sales account against the accounts profile model, wherein the plurality of existing customer sales accounts excludes the prospective customer sales account;
determine, by the database system, whether the account similarity score satisfies an account score threshold; and
recommend, by the database system, for the user, who is responsible for the plurality of existing customer sales accounts for which the accounts profile model was built, to take sales responsibility for the prospective customer sales account, in response to a determination that the account similarity score satisfies the account score threshold.
9. The computer program product of claim 8 , wherein training the machine-learning system to build the accounts profile model for the plurality of existing customer sales accounts is further based on recency-weighting each account of the plurality of existing customer sales accounts.
10. The computer program product of claim 8 , wherein training the machine-learning system to build the accounts profile model for the plurality of existing customer sales accounts comprises accommodating a missing attribute value in the plurality of existing customer sales accounts.
11. The computer program product of claim 8 , wherein training the machine-learning system to build the accounts profile model for the plurality of existing customer sales accounts is further based on a user provided attribute preference.
12. The computer program product of claim 8 , wherein the plurality of existing customer sales accounts is further associated with at least one of a plurality of users and a random sampling of existing customer sales accounts.
13. The computer program product of claim 8 , wherein training the machine-learning system to build the accounts profile model for the plurality of existing customer sales accounts comprises adjusting for an attribute dependency in plurality of existing customer sales accounts.
14. The computer program product of claim 8 , wherein training the machine-learning system to build the accounts profile model for the plurality of existing customer sales accounts is further based on at least one user success attribute associated with each account of the plurality of existing customer sales accounts.
15. A method for new account recommendations for user account sets stored in a database system, the method comprising:
training, by a database system, a machine-learning system to build an accounts profile model for a plurality of existing customer sales accounts which are a sales responsibility of a user, based on a plurality of firmographic attributes associated with each account of the plurality of existing customer sales accounts;
determining, by the database system, an account similarity score for a prospective customer sales account based on comparing a plurality of firmographic attributes associated with the prospective customer sales account against the accounts profile model, wherein the plurality of existing customer sales accounts excludes the prospective customer sales account;
determining, by the database system, whether the account similarity score satisfies an account score threshold; and
recommending, by the database system, for the user who is responsible for the plurality of existing customer sales accounts for which the accounts profile model was built, to take sales responsibility for the prospective customer sales account, in response to a determination that the account similarity score satisfies the account score threshold.
16. The method of claim 15 , wherein training the machine-learning system to build the accounts profile model for the plurality of existing customer sales accounts is further based on at least one of recency-weighting each account of the plurality of existing customer sales accounts and a user provided attribute preference.
17. The method of claim 15 , wherein training the machine-learning system to build the accounts profile model for the plurality of existing customer sales accounts comprises accommodating a missing attribute value in the plurality of existing customer sales accounts.
18. The method of claim 15 , wherein the plurality of existing customer sales accounts is further associated with at least one of a plurality of users and a random sampling of existing customer sales accounts.
19. The method of claim 15 , wherein training the machine-learning system to build the accounts profile model for the plurality of existing customer sales accounts comprises adjusting for an attribute dependency in the plurality of existing customer sales accounts.
20. The method of claim 15 , wherein training the machine-learning system to build the accounts profile model the plurality of existing customer sales accounts is further based on at least one user success attribute associated with each account of the plurality of existing customer sales accounts.