{"id":2024,"date":"2025-10-21T14:01:01","date_gmt":"2025-10-21T14:01:01","guid":{"rendered":"https:\/\/blogs.mathworks.com\/finance\/?p=2024"},"modified":"2025-10-22T09:55:37","modified_gmt":"2025-10-22T09:55:37","slug":"highlights-from-mathworks-finance-conference-2025","status":"publish","type":"post","link":"https:\/\/blogs.mathworks.com\/finance\/2025\/10\/21\/highlights-from-mathworks-finance-conference-2025\/","title":{"rendered":"Highlights from MathWorks Finance Conference 2025"},"content":{"rendered":"

\"\"<\/p>\n

The 2025 MathWorks Finance Conference brought together quants, economists, financial modelers and researchers to explore how MATLAB is shaping the future of finance. Across two days, speakers shared practical applications\u2014from pricing complex instruments to accelerating macroeconomic modelling.<\/p>\n

Here are the key highlights.<\/p>\n

Day 1: Innovation in Financial Modeling and AI<\/h1>\n
\n\n\n\n
\n
\n \"Chetan
\n <\/a><\/p>\n
Chetan Jadhav<\/div>\n
Nasdaq Private Markets<\/div>\n<\/td>\n
\n
\n \"Laura
\n <\/a><\/p>\n
Laura Ballotta<\/div>\n
Bayes Business School<\/div>\n<\/td>\n
\n
\n \"Michael
\n <\/a><\/p>\n
Michael Browne<\/div>\n
MathWorks<\/div>\n<\/td>\n
\n
\n \"Lawrence
\n <\/a><\/p>\n
Lawrence Johny<\/div>\n
MathWorks<\/div>\n<\/td>\n
\n
\n \"Michael
\n <\/a><\/p>\n
Michael Robbins<\/div>\n
Columbia University<\/div>\n<\/td>\n
\n
\n \"Taewan
\n <\/a><\/p>\n
Taewan Yoon<\/div>\n
Columbia University<\/div>\n<\/td>\n
\n
\n \"Martina
\n <\/a><\/p>\n
Martina Paez Berru<\/div>\n
Columbia University<\/div>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

 <\/p>\n

Special Purpose Vehicle (SPV) Pricing Using Physics-Informed Neural Networks<\/strong>
\nChetan Jadhav, Nasdaq Private Markets<\/em>
\nChetan introduced a pricing method for Special Purpose Vehicles (SPVs) using Physics-Informed Neural Networks (PINNs). The approach models embedded carry as a stochastic option and trains PINNs on simulated data\u2014offering a transparent method for pricing in illiquid markets.<\/p>\n

\u2192 Explore how PINNs outperform traditional models<\/a><\/p>\n

 <\/p>\n

The Calibration Conundrum: Optimizers and (Joint) Objective Functions <\/strong>
\nLaura Ballotta, Bayes Business School<\/em>
\nLaura examined the challenges of calibrating structured derivatives models. She demonstrated how joint objective functions and optimisers interact, and why calibration is more than just curve fitting\u2014it\u2019s about preserving economic meaning.<\/p>\n

\u2192 See how calibration choices affect model behaviour<\/a><\/p>\n

 <\/p>\n

\"Laura<\/p>\n

 <\/p>\n

Using MATLAB with Databricks: Orchestrate, Connect, and Deploy at Scale<\/strong>
\nMichael Browne, MathWorks<\/em>
\nMichael showcased how MATLAB integrates with Databricks to support scalable financial workflows. From JDBC queries, to deploying compiled models on Spark clusters, the session highlighted how MATLAB fits into modern data platforms.<\/p>\n

\u2192 Learn how to run MATLAB models in Databricks notebooks<\/a><\/p>\n

 <\/p>\n

MATLAB Copilot: Accelerate Robust Model Development, Testing, and Validation<\/strong>
\nLawrence Johny, MathWorks<\/em>
\nLawrence introduced MATLAB Copilot, a generative AI assistant integrated into MATLAB. Copilot assists with code comprehension, authoring, and validation, enabling faster and more robust model development.<\/p>\n

\u2192 Learn about MATLAB Copilot\u2019s editor and chat features<\/a><\/p>\n

 <\/p>\n

Investment Strategies Ideation using Large-Language Models and Structured Multi-Modal Data<\/strong>
\nMichael Robbins, Taewan Yoon, and Martina Paez Berru, Columbia University<\/em>
\nThe team presented a pipeline for generating investment ideas using large-language models and structured multi-modal data. The team used MATLAB to orchestrate data ingestion, vector analysis, and prompting\u2014surfacing niche strategies overlooked by general models.<\/p>\n

\u2192 Discover how structured prompting can uncover contrarian ideas<\/a><\/p>\n

 <\/p>\n

\"Michael<\/p>\n

Day 2: Macroeconomic Modelling and Risk Analysis<\/strong><\/h1>\n
\n\n\n\n
\n
\n \"David
\n <\/a><\/p>\n
David A. Kelley<\/div>\n
Federal Reserve Bank of New York<\/div>\n<\/td>\n
\n
\n \"Kaustubh\"
\n <\/a><\/p>\n
Kaustubh<\/div>\n
Reserve Bank of India<\/div>\n<\/td>\n
\n
\n \"Juan
\n <\/a><\/p>\n
Juan Rubio-Ram\u00edrez<\/div>\n
Emory University<\/div>\n<\/td>\n
\n
\n \"Allan
\n <\/a><\/p>\n
Allan Wright<\/div>\n
Central Bank of the Bahamas<\/div>\n<\/td>\n
\n
\n \"Eduard
\n <\/a><\/p>\n
Eduard Benet Cerd\u00e0<\/div>\n
MathWorks<\/div>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

 <\/p>\n

A MATLAB Toolbox for Mixed-Frequency State-Space Models <\/strong>
\nDavid Kelley, Federal Reserve Bank of New York<\/em>
\nDavid demonstrated the MFSS toolbox, which simplifies modelling with data observed at different frequencies. David demonstrated how to estimate high-frequency states from mixed inputs, enabling timely forecasts without aggregation loss.<\/p>\n

\u2192 See how MFSS handles quarterly and monthly data in this walkthrough<\/a><\/p>\n

 <\/p>\n

\"David<\/p>\n

 <\/p>\n

A Multi-Factor Nowcasting Model for India<\/strong>
\nKaustubh, Reserve Bank of India<\/em>
\nKaustubh introduced a multi-factor GDP nowcast model using high-frequency indicators. Kaustubh used sigmoid transformations to handle outliers and Kalman filtering to update forecasts in real time.<\/p>\n

\u2192 Review the model\u2019s performance across COVID and post-COVID periods<\/a><\/p>\n

 <\/p>\n

A Gibbs Sampler for Efficient Bayesian Inference Sign-Identified SVARs<\/strong>
\nJuan Rubio-Ram\u00edrez, Emory University<\/em>
\nJuan proposed a Gibbs sampler with elliptical slice sampling to estimate large SVARs under tight identification. This method avoids the bottlenecks of accept-reject algorithms and scales to models with many shocks.<\/p>\n

\u2192 Learn how this approach improves inference speed<\/a><\/p>\n

\u00a0<\/strong><\/p>\n

A Dynamic Stochastic General Equilibrium Analysis of a Small Open Economy with Tourism<\/strong>
\nAllan Wright, Central Bank of The Bahamas<\/em>
\nAllan used a DSGE model to simulate the impact of hurricanes on tourism-driven economies. The model showed how climate events drive output and inflation volatility, and how flexible exchange rates can help absorb shocks.<\/p>\n

\u2192 View the policy implications for small open economies<\/a><\/p>\n

 <\/p>\n

Speed Up Macroeconomic Modeling with MATLAB and Parallel Computing <\/strong>
\nEduard Benet Cerd\u00e0, MathWorks<\/em>
\nEduard shared practical ways to accelerate macroeconomic models developed in MATLAB, including those based on Dynare<\/span>. Using MATLAB parallel computing tools<\/span>\u2014from <\/span>parfor<\/span> loops to Experiment Manager\u2014the session covered how to scale estimation tasks across cores and clusters.<\/span><\/p>\n

<\/p>\n

\u2192 Find out how to reduce model runtimes from days to hours<\/a><\/p>\n

 <\/p>\n

\"Eduard<\/p>\n

If you missed the live sessions, each talk is available on demand. Whether you’re building models, pricing instruments, or forecasting macro trends, the conference offered practical insights for applying MATLAB in finance.<\/p>\n

 <\/p>\n

Browse all sessions from the 2025 conference<\/a>.<\/h2>\n","protected":false},"excerpt":{"rendered":"
<\/div>\n

\nThe 2025 MathWorks Finance Conference brought together quants, economists, financial modelers and researchers to explore how MATLAB is shaping the future of finance. Across two days, speakers shared… read more >><\/a><\/p>\n","protected":false},"author":233,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[10,22,13,16,37,4],"tags":[],"_links":{"self":[{"href":"https:\/\/blogs.mathworks.com\/finance\/wp-json\/wp\/v2\/posts\/2024"}],"collection":[{"href":"https:\/\/blogs.mathworks.com\/finance\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.mathworks.com\/finance\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.mathworks.com\/finance\/wp-json\/wp\/v2\/users\/233"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.mathworks.com\/finance\/wp-json\/wp\/v2\/comments?post=2024"}],"version-history":[{"count":56,"href":"https:\/\/blogs.mathworks.com\/finance\/wp-json\/wp\/v2\/posts\/2024\/revisions"}],"predecessor-version":[{"id":2270,"href":"https:\/\/blogs.mathworks.com\/finance\/wp-json\/wp\/v2\/posts\/2024\/revisions\/2270"}],"wp:attachment":[{"href":"https:\/\/blogs.mathworks.com\/finance\/wp-json\/wp\/v2\/media?parent=2024"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.mathworks.com\/finance\/wp-json\/wp\/v2\/categories?post=2024"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.mathworks.com\/finance\/wp-json\/wp\/v2\/tags?post=2024"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}