System and method for real-time optimization of marketing campaigns across multiple ad formats using regenerative analytics

A computer-implemented method, comprising:

• receiving, by a computer, digital creative data and ingesting historical performance data;
• evaluating, by the computer, the digital creative data for underperformance using a performance metric;
• generating, by the computer, optimized digital creative data using a respective generative model selected from among generative adversarial networks (GANs), diffusion models, and video GANs, based on the content format;
• modifying, by the computer, the digital creative content at a pixel level by performing at least one of brightness scaling, histogram-based adjustment, contrast-limited adaptive histogram equalization (CLAHE), gamma correction, diffusion-based background refinement while preserving one or more of:
• an original video subject, a text overlay enhancement, and a video pacing modification;
• deploying, by the computer, the optimized digital creative data alongside the original digital creative data for live campaign testing;
• combining, by the computer, insight from textual data, visual data, and behavioral data to identify one or more underperforming live campaigns and generate optimized variations of the live campaigns;
• identifying, by the computer, one or more high-risk campaigns and utilizing historical performance data to flag the one or more high-risk campaigns based on the performance metric;
• monitoring, by the computer, real-time performance data of live campaigns via one or more APIs;
• and
• updating, by the computer, one or more parameters of the respective generative model based on a received real-time performance data to iteratively refine subsequent regenerated digital creative content.

A computer program product for regenerative marketing analytics, the computer program product comprising:

• one or more computer-readable storage media;
• and
• program instructions stored on the one or more computer-readable storage media to perform operations comprising:
• receiving digital creative data and ingesting historical performance data;
• evaluating the digital creative data for underperformance using a performance metric;
• generating optimized digital creative data using a respective generative model selected from among GANs, diffusion models, or video GANs, based on the content type;
• modifying the digital creative content at a pixel level by performing at least one of brightness scaling, histogram-based adjustment, contrast-limited adaptive histogram equalization (CLAHE), gamma correction, diffusion-based background refinement, while preserving one or more of:
• an original video subject, a text overlay enhancement, and a video pacing modification;
• deploying the optimized digital creative data alongside the original digital creative data for live campaign testing;
• combining insight from textual data, visual data, and behavioral data to identify one or more underperforming live campaigns and generate optimized variations;
• identifying one or more high-risk campaigns and utilizing historical performance data to flag them based on the performance metric;
• monitoring real-time performance data of live campaigns via one or more APIs;
• and
• updating one or more parameters of the respective generative model based on a received real-time performance data to iteratively refine subsequent regenerated digital creative content.