Prospective battery electric vehicle (BEV) buyer analysis

A computer-implemented method for identifying prospective purchasers of battery electric vehicles (BEVs), comprising:

• defining a predetermined time frame associated with vehicle ownership;
• receiving a first dataset including a first set of driving factors, the first dataset including a first subset of drivers, a second subset of drivers, and a third subset of drivers, wherein the first dataset does not include actual BEV user data,
• wherein the first subset of drivers are drivers who have owned or leased any first internal combustion engine (ICE) vehicle followed by any second ICE vehicle within the predetermined time frame,
• wherein the second subset of drivers are drivers who have owned or leased any first ICE vehicle followed by any second BEV within the predetermined time frame, and
• wherein the third subset of drivers are drivers who have not changed vehicles within the predetermined time frame;
• training a first machine-learning (ML) model using the first subset of drivers and the second subset of drivers with their respective driving factors, wherein a first portion of the subset of drivers is used as a first training set
• and a second portion of the subset of drivers is used a first testing set;
• identifying, using the first trained ML model, a first set of prospective purchasers of BEVs from the third subset of drivers of the first dataset based on the first set of driving factors including a user's proximity to a charging station;
• receiving a second dataset including a second set of driving factors, the second dataset including a set of drivers who own or lease any first ICE vehicle which is in a same vehicle class as a target BEV and a set of drivers who currently own or lease any target BEV;
• training a second ML model using the second dataset with their respective driving factors, wherein a first portion of the second dataset is used as a first training set
• and a second portion of the second dataset is used a first testing set;
• identifying, using the second ML model, a second set of prospective purchasers of BEVs from the set of drivers of the second dataset who own or lease any first ICE vehicle which is in the same vehicle class as the target BEV;
• retraining the second ML using a confusion matrix as a second training set, wherein the confusion matrix is of actual versus predicted first ICE vehicle versus target BEV;
• and
• identifying a target set of prospective purchasers of BEVs based on the first set of prospective purchasers of BEVs and the second set of prospective purchasers of BEVs;
• and
• notifying one or more of the target set of prospective purchasers of BEVs of an incentive to purchase the target BEV.

A non-transitory computer readable storage medium storing instructions that when executed by a computer including a processor, perform a method, the method comprising:

• defining a predetermined time frame associated with vehicle ownership;
• receiving a first dataset including a first set of driving factors, the first dataset including a first subset of drivers, a second subset of drivers, and a third subset of drivers, wherein the first dataset does not include actual BEV user data,
• wherein the first subset of drivers are drivers who have owned or leased any first internal combustion engine (ICE) vehicle followed by any second ICE vehicle within the predetermined time frame,
• wherein the second subset of drivers are drivers who have owned or leased any first ICE vehicle followed by any second BEV within the predetermined time frame, and
• wherein the third subset of drivers are drivers who have not changed vehicles within the predetermined time frame;
• training a first machine-learning (ML) model using the first subset of drivers and the second subset of drivers with their respective driving factors, wherein a first portion of the subset of drivers is used as a first training set
• and a second portion of the subset of drivers is used a first testing set;
• identifying, using the first trained ML model, a first set of prospective purchasers of BEVs from the third subset of drivers of the first dataset based on the first set of driving factors including a user's proximity to a charging station;
• receiving a second dataset including a second set of driving factors, the second dataset including a set of drivers who own or lease any first ICE vehicle which is in a same vehicle class as a target BEV and a set of drivers who currently own or lease any target BEV;
• training a second ML model using the second dataset with their respective driving factors, wherein a first portion of the second dataset is used as a first training set
• and a second portion of the second dataset is used a first testing set;
• identifying, using the second ML model, a second set of prospective purchasers of BEVs from the set of drivers of the second dataset who own or lease any first ICE vehicle which is in the same vehicle class as the target BEV;
• retraining the second ML using a confusion matrix as a second training set, wherein the confusion matrix is of actual versus predicted first ICE vehicle versus target BEV;
• and
• identifying a target set of prospective purchasers of BEVs based on the first set of prospective purchasers of BEVs and the second set of prospective purchasers of BEVs;
• and
• notifying one or more of the target set of prospective purchasers of BEVs of an incentive to purchase the target BEV.