RavenPack's Aakarsh Ramchandani on unlocking alpha with NLP and LLMs

INTERVIEW: Five Minutes With…
Aakarsh Ramchandani, chief strategy officer at RavenPack | Bigdata.com 

While in NYC last week, I caught up with Aakarsh Ramchandani at Ravenpack’s office in Tribeca.

RavenPack has been developing natural language processing (NLP) products for traders since the early 2000s and recently launched a new platform, Bigdata.com, to combine LLMs with traditional NLP.

I really enjoyed our conversation about the future of AI prediction, which feels like a step toward the world imagined in Minority Report (2002). Instead of predicting crimes, we’re heading toward AI agents alerting investors to meaningful changes as they emerge.

The key word is "meaningful." The goal is to have AI agents that surface what matters - spotting early warning signs in supplier comments, or identifying how changes in one sector, like energy demand, might ripple through seemingly unrelated industries.

Hope you enjoy our chat!

This interview has been edited for clarity and length.

How did you get started at Bigdata.com?

Before Bigdata.com, I was at Third Point, where we started a data science team with a mandate: how do we leverage new technology in the alt data and quant space to enhance event-driven hedge fund strategies? I saw firsthand how hedge funds generate alpha by identifying patterns amidst noise.

At the time, I was using RavenPack, but it wasn't designed for discretionary analysts; it catered to quants analyzing statistical signals. We realized that the tools we needed didn't exist—this was around 2018 or 2019. I eventually joined RavenPack to help unlock value for a broader audience. The idea was to figure out how to unlock value with the tech we had built, making it accessible to everyone who couldn't previously handle the volume and velocity of information we produced because it was too tailored for quantitative feeds.

What makes Bigdata.com different from other tools available to investors?

Our platform is tailored for discretionary analysts and focuses on actionable insights rather than overwhelming users with raw data. For example, we don't just aggregate numbers or run keyword searches. Instead, we analyze narratives and relationships. Take earnings calls—our system doesn't just summarize them but identifies patterns and links across companies and sectors.

In one instance, we analyzed how energy demand impacts data centers, uncovering relationships across semiconductors, renewable energy firms, REITs, and even electrical substation companies. This took minutes, not days. We were able to connect narratives across the entire supply chain, highlighting how infrastructure, utilities, and renewables interact with demand for data centers—a level of insight traditional methods couldn't achieve as efficiently.

Another key differentiator is auditability. Every insight we provide is traceable. Users can hover over any bullet point to see the exact source—a paragraph or document excerpt—that led to that insight. This transparency builds trust, especially in financial decision-making, where accuracy and accountability are critical.

What about tracking events or price movements—can your platform help explain market behavior?

Absolutely. We've experimented with workflows where you can hover over a price spike on a stock chart, and the system explains the narrative driving that movement. Instead of drowning in unrelated news articles, it delivers a concise reason. For example, it might say, "This spike correlates with a supplier announcing delays that impact the company." Over time, this approach can even help identify recurring patterns and predict how certain narratives might move prices.

We're also exploring how these insights can extend to monitoring entire market sectors or thematic trends. For example, let's say there's a tariff announcement impacting toy manufacturers. Our system can identify not just the direct impact on specific companies but also downstream effects on suppliers, logistics providers, or even retailers. It's about connecting the dots between events and their broader implications.

This capability goes beyond just reporting on what happened—it can actively assist in strategy development. Users can set up alerts to track specific types of events or narratives, enabling them to respond faster and more effectively. For example, an investor could set a tracker for "earnings downgrades due to supply chain disruptions" and receive a real-time summary whenever this narrative surfaces. It's a way to systematically manage market noise and focus on actionable intelligence.

What's the ultimate vision for Bigdata.com?

Our goal is to become the go-to platform for unlocking the alpha hidden in unstructured data. We're not trying to replace human analysts but to empower them. The idea is to encode your expertise into tools that work for you, freeing you to focus on higher-level cognitive tasks. Imagine having agents that monitor specific red flags, track evolving narratives, or flag anomalies—all tailored to your investment philosophy. That's where we're heading.

Our vision extends beyond individual workflows to reshaping how investment research is conducted. We want to enable a seamless transition from idea generation to execution. For example, let's say you're tracking CEO commentary on generative AI across industries. Our platform doesn't just deliver isolated mentions—it builds a comprehensive picture, showing which companies are leading in initiatives, hiring talent, or scaling deployments. This capability can dramatically enhance both thematic investing and competitive analysis.

In the long term, we envision a world where analysts can collaborate with intelligent agents that work alongside them, not only pulling insights but also suggesting new directions to explore. These agents could autonomously monitor narratives over time, highlight shifts, and even surface opportunities before they're widely understood. The ultimate goal is to expand the surface area of what's possible in investment research, empowering analysts to generate better ideas, faster, and with greater confidence.

By bringing structure to unstructured data, we believe Bigdata.com can democratize access to insights that were once the domain of only the largest, most sophisticated investment firms. Whether it's a small hedge fund looking to scale its idea pipeline or a global bank expanding coverage from 1,200 to 5,000 companies, our platform is designed to level the playing field while enhancing the human decision-making process.

Any final thoughts on how this technology will evolve?

The next decade will be defined by how well we adapt to these new tools. The goalposts will keep shifting as people learn to game the system, but the sheer volume of opportunities this technology unlocks is transformative. We're already seeing smaller funds gain access to insights they never had before, and it's leveling the playing field in exciting ways.

ICYMI
Recent Interviews:

• PhD candidate Alex Kim on executive tone in earnings calls

• MDOTM’s Peter Zangari, PhD, on AI For Portfolio Management

• Arta’s Chirag Yagnik on AI-powered wealth management

• Finster’s Sid Jayakumar on AI agents for Wall Street

• Sov.ai's Dr. Derek Snow on AI for fundamental Investors

• Bain’s Richard Lichtenstein on AI adoption in private equity

Thanks for reading!

Drop me a line if you have story ideas, research, or upcoming conferences to share. [email protected]