yanglet

We just released the Agentic FinSearch, which is currently a Google extension. It is a user-friendly agent, a potential replacement of Bloomberg Terminal

Is it like a personal assistant that guides an individual through existing practical tools?

Any thoughts about the (financial) data sources, to avoid garbage input?

Thanks!

Thanks for sharing the links!! Appreciate it.

A few points to share:

1). Finance is high dynamic. BloombergGPT retrains LLM using a mixed dataset of finance and general sources is too much expensive (1.3M hours). Lightweight adaptation is highly favorable.

2). Internet-scale finance data (timely updates using an automatic data curation pipeline) is critical. BloombergGPT has privileged data access and API access. A promising alternative is "democratizing Internet-scale finance data".

3). Another key technology is "RLHF (Reinforcement learning from human feedback)", which is missing in BloombergGPT. RLHF enables learning individual preferences (risk-aversion level, investing habits, personalized robo-advisor, etc.)

1). Finance is high dynamic. BloombergGPT retrains LLM using a mixed dataset of finance and general sources is too much expensive (1.3M hours). Lightweight adaptation is highly favorable.

2). Internet-scale finance data (timely updates using an automatic data curation pipeline) is critical. BloombergGPT has privileged data access and API access. A promising alternative is "democratizing Internet-scale finance data".

3). Another key technology is "RLHF (Reinforcement learning from human feedback)", which is missing in BloombergGPT. RLHF enables learning individual preferences (risk-aversion level, investing habits, personalized robo-advisor, etc.)

We are aiming for feeding Internet-scale financial data into LLMs, and adapt LLMs to the finance sector. Happy to know your thoughts!

FinGPT better be open-source and open-finance.

https://news.ycombinator.com/item?id=35403167

DO NOT expect Wall Street to open-source LLMs nor open APIs.

Anyone interested in building a ChatGPT for FinTech, or FinGPT? I and my team are actively developing this project: https://github.com/AI4Finance-Foundation/ChatGPT-for-FinTech

Seems that chatGPT may help upgrade trade, like robo-advisor?

Is AI going to change algo-trading forever?

FinRL can be found here: https://github.com/AI4Finance-Foundation

There is a previous discussion here: https://news.ycombinator.com/item?id=30819436

The first author wrote several blogs about crypto trading using rl, available here: https://github.com/AI4Finance-Foundation/Blogs

Deep Reinforcement Learning for Cryptocurrency Trading: Practical Approach to Address Backtest Overfitting

Thanks for the information and sharing the paper. I also read it. Agree with you that the "simulation-to-reality gap" would be more critical to the reinforcement learning community.

NVIDIA's Isaac Gym project revealed GPU's capability of performing massively parallel simulation for gym-style environments. Detailed information can be found in the following paper:

[1] Makoviychuk, Viktor, et al. "Isaac Gym: High-Performance GPU Based Physics Simulation For Robot Learning." Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). 2021.

At its release, people commented on Twitter that "it is the MNIST moment for reinforcement learning." And over the past year, I saw several follow-up works and tested NVIDIA's implementations.

For example, a demo by this blog

https://towardsdatascience.com/a-new-era-of-massively-parall...

The question is, does that technique help advance Reinforcement Learning, as expected?

Distributed RL or Cloud-native RL?

FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning https://github.com/AI4Finance-Foundation/FinRL-Meta

A Universe of Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning.

Medium Blog at: https://medium.com/@zx2325/finrl-meta-from-market-environmen...

Learn to implement deep reinforcement learning algorithms in 24 hours.

The ElegantRL library is featured with “elegant” in the following aspects:

Lightweight: core codes have less than 1,000 lines, e.g., tutorial.

Efficient: the performance is comparable with Ray RLlib.

Stable: more stable than Stable Baseline 3.

ElegantRL supports state-of-the-art DRL algorithms, including discrete and continuous ones, and provides user-friendly tutorials in Jupyter notebooks.

The ElegantRL implements DRL algorithms under the Actor-Critic framework, where an Agent (a.k.a, a DRL algorithm) consists of an Actor network and a Critic network. Due to the completeness and simplicity of code structure, users are able to easily customize their own agents.

Using reinforcement learning to trade multiple stocks through Python and OpenAI Gym, Presented at ICAIF 2020.

A YOuTube video about FinRL: https://www.youtube.com/watch?v=ZSGJjtM-5jA

FinRL is the open source library for practitioners. To efficiently automate trading, AI4Finance provides this educational resource and makes it easier to learn about deep reinforcement learning (DRL) in quantitative finance.

In quantitative finance, automated trading is essentially making dynamic decisions, namely to decide where to trade, at what price, and what quantity, over a highlystochastic and complex stock market. Taking many complex financialfactors into account, DRL trading agents build a multi-factor model and provide algorithmic trading strategies, which are difficult for human traders

FinRL provides a framework that supports various markets, SOTA DRL algorithms, benchmarks of many quant finance tasks, live trading, etc.