Sign in Subscribe
Data

Prescient AI unveils first fundamentally new marketing mix model since 1960s

Miami company claims breakthrough in media measurement with proprietary forecasting technology built from scratch.

Luis Rijo

• 9 min read
KPI dashboard showing MMM revenue attribution across channels: Facebook Ads $1.2M, Amazon $412K, Google $646K, with daily performance trends and ROAS metrics.
KPI dashboard showing MMM revenue attribution across channels: Facebook Ads $1.2M, Amazon $412K, Google $646K, with daily performance trends and ROAS metrics.

Prescient AI announced on July 15, 2025, the launch of what the company describes as the first marketing mix model (MMM) built entirely from the ground up since MMM technology was introduced in the 1960s. The Miami-based company claims its new framework addresses limitations in existing measurement platforms that rely on decades-old regression modeling or modernized open-source models.

The announcement marks a significant development in marketing measurement at a time when brands struggle with attribution challenges. Traditional MMM platforms, according to Prescient AI's analysis, are anchored on open-source models that have been modernized but still rely on outdated mathematical foundations from previous decades.

PPC Land Newsletter

Subscribe the PPC Land newsletter ✉️ for similar stories like this one. Receive the news every day in your inbox. Free of ads. 10 USD per year.

Subscribe

Summary

Who: Prescient AI, a Miami-based marketing measurement company, along with client testimonials from David Baker (Beekman 1802) and Conner Rolain (HexClad)

What: Launch of the first marketing mix model built entirely from scratch since MMM technology introduction in the 1960s, featuring proprietary forecasting and optimization capabilities

When: Announced July 15, 2025, following extensive testing with hundreds of brands globally

Where: Miami, FL headquarters, with platform serving brands across multiple markets including direct-to-consumer, Amazon marketplace, and retail channels

Why: Address limitations in existing MMM platforms that rely on outdated mathematical foundations, provide unbiased measurement independent from media selling operations, and enable more accurate cross-channel attribution in privacy-focused marketing environment

PPC Land Newsletter

Subscribe the PPC Land newsletter ✉️ for similar stories like this one. Receive the news every day in your inbox. Free of ads. 10 USD per year.

Subscribe

"With 15 years of MMM experience, I know the difference between an incremental improvement and true innovation," said David Baker, Chief Digital Officer at Beekman 1802. "Prescient's model sets a new standard for what marketing measurement can achieve."

The timing of this announcement comes during heightened industry focus on measurement solutions. Marketing Mix Modeling has experienced renewed interest among marketing professionals as privacy regulations make traditional attribution methods more challenging.

Technical architecture addresses modern marketing dynamics

Prescient AI's proprietary model introduces several technical capabilities designed for contemporary marketing environments. The system measures what the company calls "halo effects," tracking how top-of-funnel activity impacts downstream revenue through channels that traditional models miss.

The platform delivers campaign-level insights with daily refresh rates while maintaining accuracy levels. This granular approach contrasts with traditional MMM systems that typically operate at weekly or monthly intervals.

"When we started Prescient AI, we put every available open-source model to the test," said Cody Greco, CTO and cofounder of Prescient AI. "We quickly realized that building on old technology would limit our ability to solve the complex measurement challenges facing today's marketers."

The new model identifies multiple efficiency points rather than assuming linear ad saturation applies uniformly across channels, campaigns, and brands. This mathematical approach enables the platform to detect efficiency peaks that simple saturation curves cannot reveal.

Platform features target omnichannel measurement challenges

Two primary features launched with the new model framework address specific measurement gaps. Retail Attribution provides omnichannel brands with unified media impact views across direct-to-consumer websites, wholesale channels, retail stores, Amazon, and other revenue streams within a single platform.

The second feature, Agnostic Data Ingestion, allows brands to incorporate measurement data from incrementality testing, multi-touch attribution platforms, existing MMM solutions, post-purchase surveys, and other sources. This capability enables validation of different measurement approaches against actual business outcomes.

"Optimizing paid media with incomplete data is like flying blind," said Conner Rolain, Head of Growth at HexClad. "Prescient gives us a complete, daily-updating picture of what drives sales across our ecosystem."

The platform's mathematical framework accounts for complex seasonality based on individual brand data rather than generalized industry assumptions. This customization enables brands to apply scaling decisions when efficiency peaks occur, rather than following broad market trends.

Industry context and competitive landscape

The marketing measurement sector has seen significant activity in recent months. Google's Meridian open-source MMM tool became globally available in January 2025, providing marketers with privacy-first analytics capabilities. The tool incorporates Bayesian inference and integrates with Google's advertising ecosystem.

Meta's Robyn MMM has established presence in the open-source measurement space, while Circana announced acquisitions of NCSolutions and Nielsen's Marketing Mix Modeling business in August 2024, reshaping the measurement landscape.

However, Prescient AI positions its approach differently by avoiding open-source foundations entirely. The company argues that inherent risks exist in obtaining MMM insights from vendors that also sell media, as this creates potential conflicts of interest in optimization recommendations.

The platform's independence from media selling operations addresses concerns raised by measurement experts about objectivity in attribution analysis. This positioning aligns with industry discussions about combining multiple measurement approaches for optimal results.

Mathematical innovations enable advanced capabilities

Prescient AI's technical documentation describes mathematical foundations that differ from traditional regression modeling. The system goes beyond correlation analysis to identify cause-and-effect relationships, enabling more precise forecasting and actionable optimization recommendations.

The model's approach to seasonality represents a departure from industry standards. Rather than applying generalized seasonal adjustments, the platform analyzes individual brand data patterns to identify unique efficiency windows. This capability helps marketers identify when December marketing dollars might deliver three times the impact of July spending.

Cross-channel measurement capabilities track how digital campaigns drive sales across websites, Amazon marketplaces, and physical retail stores. Traditional attribution systems typically provide partial views limited to single channels or platforms.

The platform incorporates validation mechanisms that test incrementality studies, MTA data, and other MMM results against actual business outcomes. This verification process addresses accuracy concerns that have emerged as measurement complexity increases.

Company background and funding position

Prescient AI recently received recognition as Predictive Modeling Solution of the Year in the 2025 AI Breakthrough Awards. The company serves brands including Coterie, HexClad, Jones Road Beauty, and Saatva for performance measurement, budget optimization, and growth scaling.

The company's founding team includes CTO Cody Greco, who led the technical development of the proprietary model. Marketing Communications Lead Jen Cadmus coordinates external communications from the company's Miami headquarters.

Prescient AI integrates data from multiple sources to enable brands to calibrate measurement accuracy across their complete marketing ecosystem. The platform provides forecasting capabilities across direct-to-consumer ecommerce, Amazon marketplace, and retail store sales channels.

The announcement comes at a time when measurement challenges intensify due to privacy regulations and fragmented customer journeys. Industry research suggests that combining multiple measurement approaches delivers more accurate performance pictures than relying on single methodologies.

Technical specifications and integration capabilities

The platform offers click-to-connect integration with marketing tools and channels to streamline paid media data ingestion. Onboarding specialists assist with technical implementation when needed, according to company documentation.

The system's ability to measure full-funnel impact distinguishes it from attribution models that focus on specific touchpoints. This comprehensive view enables marketers to understand how top-of-funnel investments influence downstream conversions through unexpected channels.

Daily refresh capabilities provide near real-time visibility into campaign performance across channels. This frequency enables faster optimization decisions compared to traditional MMM systems that update weekly or monthly.

The platform's efficiency peak identification represents a technical advancement over simple saturation curve analysis. Rather than assuming linear relationships between ad spend and returns, the model identifies multiple unique efficiency points for different channels and campaigns.

Market implications for measurement standards

The introduction of a fundamentally new MMM framework could influence industry measurement standards. Traditional approaches have relied on regression modeling techniques developed decades ago, with incremental improvements rather than foundational changes.

Prescient AI's emphasis on independence from media selling operations addresses growing concerns about measurement objectivity. As major advertising platforms develop their own MMM solutions, questions arise about potential conflicts of interest in optimization recommendations.

The platform's validation capabilities could establish new standards for measurement accuracy verification. By testing different attribution sources against actual business outcomes, brands can identify which measurement approaches provide reliable insights for decision-making.

The company's approach to seasonality and efficiency peaks could influence how other measurement providers model marketing dynamics. Moving beyond generalized assumptions to brand-specific data analysis represents a shift toward more personalized measurement frameworks.

Technical limitations and considerations

While Prescient AI claims breakthrough capabilities, the platform requires significant data inputs to function effectively. Brands need sufficient historical performance data across channels to enable accurate modeling and forecasting.

The platform's daily refresh capabilities depend on consistent data flow from integrated marketing tools and channels. Interruptions in data connections could impact the system's real-time measurement accuracy.

Implementation complexity may present challenges for smaller organizations without dedicated analytics resources. While onboarding specialists provide support, the platform's advanced features require understanding of marketing measurement principles.

The cost structure for accessing these advanced capabilities remains undisclosed. Traditional MMM implementations often require substantial investments that may limit adoption among smaller brands.

Prescient AI indicates plans to continue advancing the platform's mathematical foundations and measurement capabilities. The company's focus on proprietary development contrasts with industry trends toward open-source solutions and collaborative development.

The measurement industry appears headed toward hybrid approaches that combine multiple methodologies. Recent research suggests no single measurement approach addresses all marketing effectiveness challenges.

Privacy regulations continue shaping measurement innovation directions. Solutions that operate without relying on user-level data or cookies gain importance as third-party tracking capabilities diminish.

The platform's success could influence venture capital investment in measurement technology startups. Proprietary solutions that demonstrate clear advantages over open-source alternatives may attract significant funding for further development.

Terms explained

Marketing Mix Modeling (MMM): A statistical analysis technique that measures the impact of various marketing activities on sales or other business metrics. MMM uses historical data to identify which marketing channels, campaigns, or tactics drive the most revenue, allowing marketers to optimize budget allocation across different media. Unlike attribution models that track individual customer journeys, MMM takes a holistic view by analyzing aggregate data patterns to understand how marketing investments collectively influence business outcomes over time.

Halo Effects: The phenomenon where marketing activities in one channel generate additional benefits in other channels that may not be directly measurable through traditional attribution. For example, a television advertising campaign might increase brand awareness, leading to higher organic search volume, direct website traffic, or improved performance of paid search ads. These indirect effects often represent significant value that standard measurement approaches miss, making halo effect quantification crucial for accurate marketing investment assessment.

Multi-Touch Attribution (MTA): A measurement methodology that assigns credit to multiple customer touchpoints throughout the conversion journey, rather than giving all credit to the last interaction before purchase. MTA tracks individual user interactions across channels and devices to understand how different marketing activities contribute to conversions. This approach provides granular insights into customer paths to purchase but faces increasing challenges due to privacy regulations and cookie deprecation.

Incrementality Testing: Experimental methodology that measures the true causal impact of marketing activities by comparing performance between test and control groups. These tests isolate the effect of specific marketing investments by exposing one group to advertising while withholding it from another, then measuring the difference in outcomes. Incrementality testing provides definitive proof of marketing effectiveness but can be expensive and time-consuming to implement across all marketing activities.

Bayesian Inference: A statistical approach that combines prior knowledge or beliefs with new data to update probability estimates and improve model accuracy. In marketing measurement, Bayesian methods incorporate historical performance data, industry benchmarks, or expert knowledge as starting points, then refine these assumptions as new campaign data becomes available. This approach helps reduce uncertainty in measurement by building upon accumulated knowledge rather than treating each analysis as an isolated event.

Saturation Curves: Mathematical models that describe the relationship between marketing spend and diminishing returns, typically showing how additional investment in a channel yields progressively smaller incremental benefits. Traditional saturation models assume simple, linear relationships where effectiveness decreases predictably as spending increases. However, modern measurement approaches recognize that real-world saturation patterns often involve multiple efficiency peaks and varying performance dynamics across different channels and time periods.

Cross-Channel Attribution: The process of measuring how marketing activities across different platforms and channels work together to drive conversions and business outcomes. This involves tracking customer interactions that span multiple touchpoints, such as social media ads leading to email sign-ups that eventually result in retail store purchases. Cross-channel attribution addresses the challenge of understanding integrated marketing performance when customers use various devices and platforms throughout their journey.

Omnichannel Measurement: Comprehensive tracking and analysis of marketing performance across all customer touchpoints and sales channels, including digital platforms, physical stores, marketplaces, and other revenue streams. This approach recognizes that modern customers interact with brands through multiple channels and requires measurement systems that can connect activities across online and offline environments to provide a complete view of marketing effectiveness and customer behavior patterns.

Regression Modeling: A statistical technique that analyzes relationships between variables to predict outcomes and understand how changes in marketing inputs affect business results. Traditional MMM platforms rely heavily on regression analysis to identify correlations between marketing activities and sales performance. While regression modeling has been the foundation of marketing measurement for decades, critics argue that these approaches may miss complex, non-linear relationships that characterize modern marketing dynamics.

Agnostic Data Ingestion: The capability to incorporate and analyze data from multiple measurement sources and platforms without being limited to specific vendors or methodologies. This approach allows marketers to combine insights from various attribution models, testing frameworks, survey data, and measurement platforms to create more comprehensive performance assessments. Agnostic systems enable validation of different measurement approaches against each other and against actual business outcomes for improved decision-making accuracy.

Timeline