Methods and systems for providing estimated transactional data

1. A computer-implemented method for estimating utility transaction data, comprising:

obtaining, via one or more processors and from one or more transactional entities, historical utility transactional data of one or more customers associated with an address within a geographical region, the geographical region including a plurality of sub-regions;

generating anonymized historical utility transactional data by:

disassociating the historical utility transactional data of each customer from the address of the customer; and

associating the historical utility transactional data of each customer with a sub-region of the geographical region that includes the address of the customer;

determining, via the one or more processors and based on the anonymized historical utility transactional data, estimated transactional utility data of each sub-region, wherein:

the estimated transactional utility data is determined based on one or more historical heatmaps of the anonymized historical utility transactional data; and

determining the estimated transactional utility data includes using a trained machine-learning model that has been trained, based on sequences of training heatmaps, to generate a forecast heatmap in response to input of the one or more historical heatmaps;

generating, via the one or more processors and based on the determined estimated utility transactional data of the sub-regions, a heatmap indicative of the geographical region and of estimated utility transactional data corresponding to the sub-regions;

causing, via the one or more processors, a display of a computer system to output the generated heatmap via a graphical user interface;

receiving, via the graphical user interface, a user interaction specifying at least one of a specific address or a specific sub-region; and

in response to receiving the user interaction, causing an update of the output of the heatmap based on the at least one specific address or specific sub-region.

2. The computer-implemented method of claim 1 , further comprising:

receiving, from the graphical user interface, historical utility transactional data of a user associated with the specific address or specific sub-region;

comparing the received historical utility transactional data of the user with the estimated utility transactional data corresponding to the specific sub-region or a sub-region including the specific address;

generating an indication based on the comparing; and

causing the graphical user interface to output the indication.

3. The computer-implemented method of claim 2 , wherein the indication includes a strategy for reducing a utility cost of the user.

4. The computer-implemented method of claim 2 , wherein the indication includes a utility cost budget for the user for a predetermined period of time.

5. The computer-implemented method of claim 1 , wherein the trained machine-learning model includes one or more of a convolutional neural network or a recurrent neural network.

6. The computer-implemented method of claim 1 , wherein estimated transactional utility data is a future utility cost forecast.

7. The computer-implemented method of claim 6 , further comprising:

receiving, via the graphical user interface, one or more of a future point in time or a forecast period; and

determining, based on the future utility cost forecast, a utility cost one or more of at the future point in time or over the forecast period.

8. The computer-implemented method of claim 1 , wherein:

the historical utility transactional data of the one or more customers includes one or more of demographic data or behavior data;

the computer-implemented method further comprises obtaining one or more demographic data or behavior data of a user; and

the estimated transactional utility data is determined based on the demographic data or behavior data of the user and of the one or more customers.

9. A system for estimating utility transaction data, comprising:

at least one memory storing instructions and a trained machine-learning model that has been trained, based on sequences of training heatmaps, to generate a forecast heatmap in response to input of one or more historical heatmaps; and

at least one processor operatively connected to the at least one memory, and configured to execute the instructions to perform operations, including:

obtaining, from one or more transactional entities, historical utility transactional data of one or more customers associated with an address within a geographical region, the geographical region including a plurality of sub-regions;

generating anonymized historical utility transactional data by:

disassociating the historical utility transactional data of each customer from the address of the customer; and

associating the historical utility transactional data of each customer with a sub-region of the geographical region that includes the address of the customer;

determining, based on the anonymized historical utility transactional data, estimated transactional utility data of each sub-region, wherein:

the estimated transactional utility data is determined based on the one or more historical heatmaps of the anonymized historical utility transactional data; and

determining the estimated transactional utility data includes using the trained machine-learning model;

generating, based on the determined estimated utility transactional data of the sub-regions, a heatmap indicative of the geographical region and of estimated utility transactional data corresponding to the sub-regions;

causing a display of a computer system to output the generated heatmap via a graphical user interface;

receiving, via the graphical user interface, a user interaction specifying at least one of a specific address or a specific sub-region; and

in response to receiving the user interaction, causing an update of the output of the heatmap based on the at least one specific address or specific sub-region.

10. The system of claim 9 , wherein the operations further include:

receiving, from the graphical user interface, historical utility transactional data of a user associated with the specific address or specific sub-region;

comparing the received historical utility transactional data of the user with the estimated utility transactional data corresponding to the specific sub-region or a sub-region including the specific address;

generating an indication based on the comparing; and

causing the graphical user interface to output the indication.

11. The system of claim 10 , wherein the indication includes one or more of a strategy for reducing a utility cost of the user or a utility cost budget for the user for a predetermined period of time.

12. The system of claim 9 , wherein the trained machine-learning model includes one or more of a convolutional neural network or a recurrent neural network.

13. The system of claim 9 , wherein estimated transactional utility data is a future utility cost forecast.

14. The system of claim 13 , wherein the operations further include:

receiving, via the graphical user interface, one or more of a future point in time or a forecast period; and

determining, based on the future utility cost forecast, a utility cost one or more of at the future point in time or over the forecast period.

15. The system of claim 9 , wherein:

the historical utility transactional data of the one or more customers includes one or more of demographic data or behavior data;

the operations further include obtaining one or more demographic data or behavior data of a user; and

the estimated transactional utility data is determined based on the demographic data or behavior data of the user and of the one or more customers.

16. A computer-implemented method for estimating utility transaction data, comprising:

obtaining, via one or more processors and from one or more transactional entities, historical utility transactional data of one or more customers associated with an address within a geographical region, the geographical region including a plurality of sub-regions;

generating anonymized historical utility transactional data by:

disassociating the historical utility transactional data of each customer from the address of the customer; and

associating the historical utility transactional data of each customer with a sub-region of the geographical region that includes the address of the customer;

determining estimated transactional utility data of each sub-region by inputting one or more historical heatmaps of the anonymized historical utility transactional data into a trained-machine learning model that has been trained, based on sequences of training heatmaps, to generate a forecast heatmap in response to input of the one or more historical heatmaps;

generating, via the one or more processors and based on the determined estimated utility transactional data of the sub-regions, a heatmap indicative of the geographical region and of estimated utility transactional data corresponding to the sub-regions;

causing, via the one or more processors, a display of a computer system to output the generated heatmap via a graphical user interface;

receiving, via the graphical user interface, a user interaction specifying at least one of a specific address or a specific sub-region; and

in response to receiving the user interaction, causing an update of the output of the heatmap based on the at least one specific address or specific sub-region.