Systems and methods for collaborative offer generation

A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to:

• receive a proposed offer from a manufacturer, wherein the proposed offer includes a number of consumers to target, a product, and an offer structure;
• access transaction logs describing a plurality of transactions completed by a plurality of consumers with a retailer;
• compute a set of metrics for each consumer of the plurality of consumers based on the accessed transaction logs, wherein the set of metrics for a consumer of the plurality of consumers comprises:
• a first metric indicating whether the consumer has previously purchased the product associated with the proposed offer;
• a second metric indicating a price elasticity of the consumer for the product;
• and
• a third metric indicating how frequently the consumer purchases the product;
• receive a set of shopper weight values from the retailer, wherein each shopper weight value of the set of shopper weight values corresponds to a metric of the set of metrics;
• calculate a return on investment (ROI) value for each consumer of the plurality of consumers, wherein calculating the ROI value for a consumer comprises multiplying each metric of the set of metrics associated with the consumer by a corresponding shopper weight value of the set of shopper weight values;
• generate an ROI distribution comprising a plurality of consumer buckets, wherein each consumer bucket of the plurality of consumer buckets comprises consumers of the plurality of consumers associated with ROI values that are within a percentile range of ROI values, and wherein each consumer bucket of the plurality of consumer buckets comprises the same number of consumers;
• select a subset of the plurality of consumer buckets associated with the largest percentile ranges of the plurality of consumer buckets, wherein a number of consumer buckets selected for the subset of consumer buckets is based on the number of consumers to target associated with the proposed offer;
• calculate an average ROI value based on the ROI values associated with consumers in the selected subset of consumer buckets.

A system comprising:

• a processor;
• and
• a non-transitory computer-readable medium storing instructions that, when executed by the processor, cause the processor to:
• receive a proposed offer from a manufacturer, wherein the proposed offer includes a number of consumers to target, a product, and an offer structure;
• access transaction logs describing a plurality of transactions completed by a plurality of consumers with a retailer;
• compute a set of metrics for each consumer of the plurality of consumers based on the accessed transaction logs, wherein the set of metrics for a consumer of the plurality of consumers comprises:
• a first metric indicating whether the consumer has previously purchased the product associated with the proposed offer;
• a second metric indicating a price elasticity of the consumer for the product;
• and
• a third metric indicating how frequently the consumer purchases the product;
• receive a set of shopper weight values from the retailer, wherein each shopper weight value of the set of shopper weight values corresponds to a metric of the set of metrics;
• calculate a return on investment (ROI) value for each consumer of the plurality of consumers, wherein calculating the ROI value for a consumer comprises multiplying each metric of the set of metrics associated with the consumer by a corresponding shopper weight value of the set of shopper weight values;
• generate an ROI distribution comprising a plurality of consumer buckets, wherein each consumer bucket of the plurality of consumer buckets comprises consumers of the plurality of consumers associated with ROI values that are within a percentile range of ROI values, and wherein each consumer bucket of the plurality of consumer buckets comprises the same number of consumers;
• select a subset of the plurality of consumer buckets associated with the largest percentile ranges of the plurality of consumer buckets, wherein a number of consumer buckets selected for the subset of consumer buckets is based on the number of consumers to target associated with the proposed offer;
• calculate an average ROI value based on the ROI values associated with consumers in the selected subset of consumer buckets.