iiinova — where your digital self keeps evolving

Suproteem Sarkar

@suproteem.cc

Assistant Professor, Chicago Booth Harvard AB/SM ‘19, PhD ‘25 Website: suproteem.cc

Suproteem Sarkar @suproteem.cc · 20/11/2024

I’m excited to further study questions related to finance, technology+innovation, and behavioral economics, and to extend the scope and credibility of machine learning in empirical research You can find the full paper at suproteem.cc/representati...

suproteem.cc

020

Suproteem Sarkar @suproteem.cc · 20/11/2024

In summary: I transform economic language into embedding vectors, and show these vectors are informative of perceptions and beliefs I train LLMs that address credibility issues with ML in empirical research I study economic mechanisms that drive valuation and misvaluation

100

Suproteem Sarkar @suproteem.cc · 20/11/2024

Valuations can fluctuate when perceptions change—is a customer service firm that adopts a language model really an “AI” firm, or just a “service” firm? I find that these perception changes relate to selective attention, firm communication, and technology transformations

120

Suproteem Sarkar @suproteem.cc · 20/11/2024

Main results: 1️⃣ Embeddings explain valuations + outperform traditional characteristics 2️⃣ Returns reflect changes in how businesses are valued + changes in the perceived business model itself 3️⃣ Some changes in embeddings reflect misperceptions, which generate misvaluation

110

Suproteem Sarkar @suproteem.cc · 20/11/2024

Embeddings also encode similarity between firms—geometric distance relates to established measures of perceived similarity Taken together, these results demonstrate that a firm’s embedding is informative of its perceived business model

110

Suproteem Sarkar @suproteem.cc · 20/11/2024

First, I train new language models on historical data to avoid lookahead bias. I’ve released these LLMs to the research community Second, I use contrastive representation learning to construct embeddings of firms. The geometry of these vectors relates to economic features of firms

100

Suproteem Sarkar @suproteem.cc · 20/11/2024

I transform financial news language into embedding vectors Embeddings put quantitative structure on unstructured data, and have contributed to the success of machine learning over the past decade

100

Suproteem Sarkar @suproteem.cc · 20/11/2024

Economic valuations fluctuate in ways empirical research cannot fully explain What information are we missing? Economic theories emphasize the role of hard-to-quantify beliefs and perceptions My job market paper develops algorithms + measurement to quantify perceptions of firms

1178