{"id":"CU26312","slug":"digital-twin-synthetic-survey--CU26312","source":{"id":"CU26312","dataset":"techtransfer","title":"Digital twin synthetic survey platform for AI-generated panel research","description_":"<p>This technology is an AI-powered digital twin survey and panel research platform that generates synthetic respondents from historical survey and persona data to enable rapid, low-cost market research, concept testing, and structured user feedback.</p>\r\r<h2>Unmet Need: Rapid, low-cost alternative to traditional human survey research</h2>\r\r<p>Current survey and panel research relies heavily on recruiting human participants, a process that is often expensive, time-consuming, and operationally complex. Organizations frequently wait for long periods to field surveys, collect responses, and conduct follow-up studies, limiting the speed of decision-making and iterative testing. Existing synthetic research tools are often fragmented, enterprise-focused, or limited to narrow use cases, leaving smaller organizations and academic researchers without accessible alternatives. There is a growing need for scalable research approaches that can rapidly generate structured insights while reducing the cost, logistical burden, and turnaround time associated with traditional human-subject research.</p>\r\r<h2>The Technology: AI-generated digital twin platform for scalable synthetic survey research</h2>\r\r<p>This platform generates synthetic research participants, or digital twins, using historical survey records and persona-based data from publicly accessible and verifiable sources. It supports ingestion of structured survey instruments while preserving key survey logic such as branching, randomization, and multi-section workflows. The system converts AI-generated outputs into structured survey responses and automatically produces summary statistics, charts, open-ended insights, and downloadable reports. It also supports persistent digital twin identities for follow-up interviews, panel-style interactions, and feedback on uploaded documents or media.</p>\r\r<h2>Applications:</h2>\r\r<ul>\r<li>Scalable research infrastructure for market research and consumer insights</li>\r<li>Product concept and message testing</li>\r<li>User experience and customer feedback research</li>\r<li>Healthcare and patient communication testing</li>\r<li>Synthetic panel and longitudinal interviews</li>\r<li>Advertising and branding research</li>\r<li>Rapid iterative feedback for product development</li>\r</ul>\r\r<h2>Advantages:</h2>\r\r<ul>\r<li>Reduces survey time and operational costs</li>\r<li>Enables rapid iterative research</li>\r<li>Preserves complex survey logic</li>\r<li>Supports longitudinal panel studies</li>\r<li>Automatically generates reports and insights</li>\r<li>Scalable synthetic panel platform</li>\r<li>Minimizes participant recruitment burden</li>\r<li>Combines simulation and analysis in one platform</li>\r</ul>\r\r<h2>Lead Inventor:</h2>\r\r<p><a href=\"https://datascience.columbia.edu/people/olivier-toubia/\">Olivier Toubia, Ph.D.</a></p>\r\r<h2>Related Publications:</h2>\r\r<ul>\r<li><p><a href=\"https://arxiv.org/html/2509.19088v5\">Peng T, Gui G, Brucks M, Merlau DJ, Fan GJ, Ben Sliman M, Johnson EJ, Althenayyan A, Bellezza S, Donati D, Fong H, Friedman E, Guevara A, Hussein M, Jerath K, Kogut B, Kumar A, Lane K, Li H, Morwitz V, Netzer O, Perkowski P, Toubia O. “Digital Twins are Funhouse Mirrors: Five Systematic Distortions.” arXiv. 2026 Apr 19.</a></p></li>\r<li><p><a href=\"https://arxiv.org/html/2509.19088v3\">Peng T, Gui G, Merlau DJ, Fan GJ, Ben Sliman M, Brucks M, Johnson EJ, Morwitz V, Althenayyan A, Bellezza S, Donati D, Fong H, Friedman E, Guevara A, Hussein M, Jerath K, Kogut B, Kumar A, Lane K, Li H, Perkowski P, Netzer O, Toubia O. “A Mega-Study of Digital Twins Reveals Strengths, Weaknesses and Opportunities for Further Improvement.” arXiv. 2025 Nov 7.</a></p></li>\r</ul>\r\r<h2>Tech Ventures Reference:</h2>\r\r<ul>\r<li><p>IR CU26312</p></li>\r<li><p>Licensing Contact: <a href=\"mailto:techtransfer@columbia.edu\">Joan Martinez</a></p></li>\r</ul>\r","tags":["Communication","Digital twin","User experience"],"file_number":"CU26312","collections":[],"meta_description":"AI-powered digital twin platform for scalable synthetic survey research, enabling rapid, low-cost, longitudinal insights with automated reports.","apriori_judge_output":"{\"scores\":{\"novelty\":3.0,\"potential_impact\":4.0,\"readiness\":4.0,\"scalability\":4.0,\"timeliness\":3.0},\"weighted_score\":3.65,\"risks\":[\"Late-stage novelty concerns (digital twin for surveys may be incremental over prior synthetic data work)\",\"Regulatory/privacy constraints with synthetic respondent data\",\"Data quality and bias risks in longitudinal synthetic panels\",\"Dependency on proprietary datasets for calibration\",\"Market adoption risk in enterprise MR space\"],\"one_sentence_take\":\"Solid near-term potential with strong readiness and scalability, but novelty moderate and timeliness contingent on privacy-bias safeguards and market uptake.\"}","inventors":["Naveen Venkatanarayanan","Olivier Toubia","Tianyi Peng Ph.D.","Zhida Gui"],"manager":"Joan Martinez","depts":["Columbia Business School"],"divs":["Columbia Business School"],"date_released":"2026-05-29"},"highlight":{},"matched_queries":null,"score":0.0}