Systems and methods for deriving leading indicators of future manufacturing, production, and consumption of goods and services

A method of providing a leading indicator of economic activity, the method comprising:

• receiving a plurality of datasets from a corresponding plurality of data sources, wherein at least one of the plurality of datasets includes first sensor data derived from direct observation of activity within an environment;
• assigning, with a data preparation module, metadata to the stored datasets;
• training, with at least one predictive analytics module, first and second machine learning models using the stored datasets as a source of predictor variables based on the assigned metadata for each of the machine learning models, and using historical information regarding a metric of the economic activity as a target variable;
• and providing, to one or more subscribers, model information and output data including a leading indicator of the target variable based on the trained machine learning model and contemporaneous information received from at least one of the data sources;
• wherein training the first and second machine learning models, selecting the predictor variables for the machine learning models, and determining the leading indicator is performed by a hypothesis generating and testing system (HGTS) using the assigned metadata for the machine learning models;
• further including, for each of the first and second machine learning models, the steps of compiling and rank-ordering data correlations for the machine learning models based on statistical significance of the data correlations;
• storing the assigned metadata, the first machine learning model, and the predictor variables in a primary database in response to determining that the first machine learning model exhibits a statistically significant correlation;
• storing the assigned metadata, the second machine learning model, and the predictor variables in a second, probationary database in response to determining that if the second machine learning model exhibits a correlation that is not statistically significant but is above a minimum correlation value, and selecting between machine learning models based on their respective data correlations;
• wherein the first and second machine learning models differ in at least one of:
• machine learning model type and assigned metadata;
• and wherein the metadata includes at least:
• data collection methods for the first sensor data;
• data preparation methods for the first sensor data;
• and at least one of accuracy, precision, or resolution of the first sensor data.

A predictive analytics system comprising:

• a plurality of datasets received from a corresponding plurality of data sources, wherein at least one of the plurality of datasets includes first sensor data derived from direct observation of activity within an environment, and the first sensor data includes imaging data documenting transportation activity in the environment, wherein the transportation activity corresponds to the type and behavior of vehicles on a section of roadway, and the data source associated with observation of the transportation activity is at least one of a traffic camera, a satellite imaging system, and an aerial imaging system accessible remotely via a network;
• a data preparation module, including a processing device, configured to assign metadata to the stored datasets;
• at least one predictive analytics module, including a processing device, configured to train first and second machine learning models using the stored datasets as a source of predictor variables based on the assigned metadata for each of the machine learning models, and using historical information regarding a metric of economic activity as a target variable, the machine learning models configured to perform object detection and classification with respect to the vehicles observed in the first sensor data, wherein the predictor variables include the respective types and motions of the vehicles;
• and a publishing module, including a processing device, configured to provide, to one or more subscribers, model information and output data including a leading indicator of the target variable based on the trained machine learning model and contemporaneous information received from at least one of the data sources;
• a hypothesis generating and testing system (HGTS) that performs training the first and second machine learning models, selecting the predictor variables for the machine learning models, and determining the leading indicator using the assigned metadata for the machine learning models;
• the HGTS including, for each of the first and second machine learning models, an analytics engine configured to:
• (a) compile and rank-order data correlations for the machine learning models based on statistical significance of the data correlations;
• (b) store the assigned metadata, the first machine learning model, and the predictor variables in a primary database in response to determining that if the first machine learning model exhibits a statistically significant correlation, (c) store the assigned metadata, the second machine learning model, and the predictor variables in a second, probationary database in response to determining that the machine second learning model exhibits a correlation that is not statistically significant but is above a minimum correlation value, and (d) select between machine learning models based on their respective data correlations;
• wherein the first and second machine learning models differ in at least one of:
• machine learning model type and assigned metadata;
• wherein the metadata includes at least:
• data collection methods for the first sensor data;
• data preparation methods for the first sensor data;
• and at least one of accuracy, precision, or resolution of the first sensor data.