Flirting with Models

Flirting with Models is the show that aims to pull back the curtain and meet the investors who research, design, develop, and manage quantitative investment strategies.

Bin Ren – text2quant (S7E2)

S7 E2 • Dec 11, 2023 • 77 mins

Corey Hoffstein and Bin Ren explore the intersection of AI and finance, focusing on the integration of large language models into systematic trading. They discuss Bin's transition from Brevin Howard to developing advanced backtesting engines and the importance of coupling these with data models. The episode delves into the flexibility of trading timing, incorporating alternative data, and integrating AI models like ChatGPT. They address the challenges of API design, handling queries, and understanding context in language models. The conversation covers the shift from code-centric to text-based strategies and the evolving role of quant researchers with AI. Cultural perspectives on AI in finance and future implications are also explored.

In this episode I speak with Bin Ren, founder of SigTech, a financial technology platform providing quantitative researchers with access to a state-of-the-art analysis engine.

This conversation is really broken into two parts. In the first half, we discuss Bin’s views on designing and developing a state-of-the-art backtesting engine. This includes concepts around monolithic versus modular design, how tightly coupled the engine and data should be, and the blurred line between where a strategy definition ends and the backtest engine begins.

In the second half of the conversation we discuss the significant pivot SigTech has undergone this year to incorporate large language models into its process. Or, perhaps more accurately, allow large language models to be a client to its data and services. Here Bin shares his thoughts on both the technical ramifications of integrating with LLMs as well as his philosophical views as to how the role of a quant researcher will change over time as AI becomes more prevalent.

I hope you enjoy my conversation with Bin Ren.

Speakers

Corey Hoffstein

Host • 14%

Bin Ren

Guest • 69%

Bin Ren

Guest • 17%

Chapters

0:00	Introduction and show promotion
1:21	Guest introduction and background
2:09	AI and large language models in finance
9:05	Transition to systematic trading and lessons from Brevin Howard
15:53	Developing a state of the art backtesting engine
22:24	Coupling backtesting engines with data models
25:50	Trading timing flexibility and backtesting engine designs
28:15	Incorporating alternative data into strategies
31:43	Integrating large language models into backtesting
37:20	Diligence for integrating ChatGPT and other LLMs
42:36	API design philosophies for LLMs
52:51	Handling queries and constructing returns with LLMs
57:31	Understanding implicit context and nuances in LLMs
1:02:11	Transition from code-centric to text-based strategies
1:06:48	Adapting to API changes in LLMs
1:08:06	The future role of quant researchers with AI
1:11:14	Cultural perspectives on AI in finance
1:16:16	Final thoughts and sign-off

Transcript

Loading transcript...

- / -