Identifying and processing marketing leads that impact a seller's enterprise valuation
Systems, methods and computer readable media for automated marketing decisions based on company valuation results derived from ensemble machine learning models include collecting potential customer data for a set of potential customers from a lead source and transmitting the potential customer data to an optimization system. An ensemble machine learning model that establishes a transaction value for each of the set of potential customers based on an enterprise valuation of the seller. A marketing action is then taken. The marketing action may include one or more of budgeting for a transaction with the lead source, targeting communications to members of the set of potential customers, accepting or rejecting members of the set of potential customers, or offloading members of the set of potential customers.
1 . A computer implemented method, comprising:
determining an objective function indicative of an impact of a transaction on an enterprise valuation, wherein the objective function is determined based on selecting a plurality of factors relevant to an enterprise and assigning to each factor a corresponding weight of a plurality of weights, wherein each assigned weight is indicative of the relevance of the corresponding factor to the enterprise valuation;
training, based on the objective function and a training data set, an ensemble of machine learning models to determine an indication of the enterprise valuation, wherein the ensemble of machine learning models account for the plurality of factors relevant to the enterprise, wherein training the ensemble of machine learning models comprises performing an iterative process that iteratively adds one or more machine learning models to the ensemble of machine learning models by:
testing a plurality of machine learning models with a testing data set, wherein the testing data set comprises at least transaction data,
determining an evaluation metric value for each of the plurality of machine learning models, and
selecting, based on comparing the evaluation metric values to each other, a portion of the plurality of machine learning models that optimize the objective function, wherein the iterative process optimizes the ensemble to obtain a group of machine learning models of multiple different types of machine learning that collectively optimize the objective function;
receiving potential customer data for a potential customer associated with a lead source;
determining, based on inputting the potential customer data into the ensemble of machine learning models, an indication of the enterprise valuation, of the enterprise, associated with a potential transaction of the potential customer; and
causing, based on transaction data associated with the potential customer, the ensemble of machine learning models to be updated.
2 . The computer implemented method of claim 1 , further comprising determining, based on the indication of the enterprise valuation, content, wherein the content comprises one or more messages from a collection of messages associated with a potential customer content data store.
3 . The computer implemented method of claim 1 , wherein the plurality of factors comprises one or more of a cost of customer acquisition, a customer lifetime value, a return on capital, a percentage paid, or a first payment default recovered.
4 . The computer implemented method of claim 1 , further comprising sending a communication associated with causing monetization of lead information of the potential customer if the potential transaction does not occur.
5 . The computer implemented method of claim 4 , wherein sending the communication associated with causing monetization of the lead information of the potential customer comprises sending a communication associated with causing sale of the lead information of the potential customer to a third party.
6 . The computer implemented method of claim 1 , further comprising applying the potential customer data to one or more filters configured to identify potential customers associated with a positive impact on the enterprise valuation of the enterprise.
7 . The computer implemented method of claim 6 , further comprising determining to accept the potential customer, and determining, based on available customer volume and the indication of the enterprise valuation associated with the potential customer, acceptance data associated with the potential customer.
8 . The computer implemented method of claim 7 , further comprising sending, to the lead source and based on determining to accept the potential customer, a message comprising acceptance data associated with the potential customer.
9 . The computer implemented method of claim 1 , further comprising:
processing a transaction of the potential customer; and
determining the transaction data associated with the potential customer, wherein the transaction data is associated with the transaction.
10 . The method of claim 1 , wherein causing the ensemble of machine learning models to be updated comprises one or more of retraining the ensemble of machine learning models or generating one or more additional ensemble of machine learning models based on the prior trained ensemble of machine learning models.
11 . The method of claim 1 , wherein the iterative process comprises evaluating performance of a machine learning model both individually and as part of the ensemble of machine learning models.
12 . The method of claim 1 , further comprising:
causing an update to the objective function based on receiving data indicating a change to the objective function associated with changes in enterprise conditions; and
causing, based on the update to the objective function, the ensemble of machine learning models to be updated.
13 . A system comprising:
a processor;
a machine-readable medium coupled to the processor, the machine-readable medium including processor implementation-specific instructions that, if executed by the processor, will cause the processor to perform operations including:
determining an objective function indicative of an impact of a transaction on an enterprise valuation, wherein the objective function is determined based on selecting a plurality of factors relevant to an enterprise and assigning to each factor a corresponding weight of a plurality of weights, wherein each assigned weight is indicative of the relevance of the corresponding factor to the enterprise valuation;
training, based on the objective function and a training data set, an ensemble of machine learning models to determine an indication of the enterprise valuation, wherein the ensemble of machine learning models accounts for the plurality of factors relevant to the enterprise, wherein training the ensemble of machine learning models comprises performing an iterative process that iteratively adds one or more machine learning models to the ensemble of machine learning models by:
testing a plurality of machine learning models with a testing data set, wherein the testing data set comprises at least transaction data,
determining an evaluation metric value for each of the plurality of machine learning models, and
selecting, based on comparing the evaluation metric values to each other, a portion of the plurality of machine learning models that optimize the objective function, wherein the iterative process optimizes the ensemble to obtain a group of machine learning models of multiple different types of machine learning that collectively optimize the objective function;
receiving potential customer data for a potential customer associated with a lead source;
determining, based on inputting the potential customer data into the ensemble of machine learning models, an indication of the enterprise valuation, of the enterprise, associated with a potential transaction of the potential customer; and
causing, based on transaction data associated with the potential customer, the ensemble of machine learning models to be updated.
14 . The system of claim 13 , further comprising instructions that, if executed by the processor, will cause the processor to perform operations including determining, based on the indication of the enterprise valuation, content, wherein the content comprises one or more messages from a collection of messages associated with a potential customer content data store.
15 . The system of claim 13 , wherein the plurality of factors comprise one or more of a cost of customer acquisition, a customer lifetime value, a return on capital, percentage paid, or a first payment default recovered.
16 . The system of claim 13 , further comprising instructions that, if executed by the processor, will cause the processor to perform operations including sending a communication associated with causing monetization of lead information of the potential customer if the potential transaction does not occur.
17 . The system of claim 13 , further comprising instructions that, if executed by the processor, will cause the processor to perform operations including applying the potential customer data to one or more filters configured to identify potential customers associated with a positive impact on the enterprise valuation.
18 . The system of claim 17 , further comprising instructions that, if executed by the processor, will cause the processor to perform operations including determining to accept the potential customer, and determining, based on available customer volume and the indication of the enterprise valuation associated with the potential customer, acceptance data associated with the potential customer.
19 . The system of claim 18 , further comprising instructions that, if executed by the processor, will cause the processor to perform operations including sending, to the lead source and based on determining to accept the potential customer, a message comprising acceptance data associated with the potential customer.
20 . The system of claim 13 , further comprising instructions that, if executed by the processor, will cause the processor to perform operations including:
processing a transaction of the potential customer; and
determining the transaction data associated with the potential customer, wherein the transaction data is associated with the transaction.