Fine-tuning NER vs LLM prompt for asset ticker extraction in finance UGC
With the increasing multiple-task capability of LLM model, it makes it easy to do specific ML task by prompting LLM to focus on specified task, such as sentiment classification, name entity recognition, document analysis, OCR, et al. Before LLM, it...
Resource sharing for AI fintech product development
# Fintech product development collection- Common financial risk and performance metrics. Used by zipline and pyfolio, [empyrical](https://github.com/quantopian/empyrical/tree/master)- Python library for performance and risk analysis of financial portfolios that works well with the Zipline open source backtesting library. [pyfolio](https://github.com/stefan-jansen/pyfolio-reloaded/tree/main)- Bayesian Modeling...
How to solve aiohttp.ClientSession failure: Client error for XXX: Can not write request body for API_URL
aiohttp_ClientSession_issueInvestigate aiohttp.ClientSession randomly failure when batch calling APIs, e.g. Client error for XXX: Can not write request body for API_URLWhat is the issue?The issue happends when you call your API endpoint (e.g. FastAPI server) from server side using batch. Normally...
AGI, I don’t expect what I can see.
AGI, not PR AGI, is not possible, at least in next years. But text, vision, multi-modal foundation models make it easy to develop AI/ML based applications using domain knowledge to tailor llm to act as classifier, entity extractor, relation extraction,object...
Remote conntection disconnected in FastAPI server
When I develop LLM agent based service (e.g. call openAI api async) using multiple workers to parallel processing large requests, I use uvicorn in APP code to start multiple workers. In server side, a ```remote conntection disconnected``` error happens. But...
Daily update signal forecasting for QQQ [Update 2024-11-26]
Currently I am working on FinAgent, leverage LLM to analyze historical price, LLM agent, reflection, and reinforcement learning to forecast signal for stock. After doing a lot experiments using about 10 stocks such as QQQ, SPY, SQQQ, NVDA, TSLA, KO,...
LLM in finance: paper collection
Based on preliminary results, LLM + agent + reflection looks positive in stock market information fusion and signal prediction. The following are paper list collected.FinLlama: Financial Sentiment Classification for Algorithmic Trading Applications, https://arxiv.org/pdf/2403.12285Alpha-GPT: Human-AI Interactive Alpha Mining for Quantitative, https://arxiv.org/pdf/2308.00016RLAIF...
Summary of overseas scholarship for Singaporean and PR in Singapore
There are many scholarships available for Singaprean and PR to support students to pursue undergraduate study in local or overseas, which scholarships are from government and industry (Famous companies in Singapore). Most scholarships can support overseas or local study. In...
Why your fastapi response slow, even after increasing computing resource
FastAPI is a poppolar framework to build API service. It is easy to use, fast and support async requests. FastAPI support multiple workers and parallel high volume (middle level) requests. But when you quickly develop an API using the default...
How to install Phi-3-vision 128k onnx
Open-source LLMs (text modality) are involution and competitive among the AI companies. There are also quantization optimized small LLMs available (e.g. llm.cpp, ollama), which are running realtime in the low-memory consumer GPU (e.g. 4070 10GB for me), and even CPUs...
How to patch Python project into executable command
It is not easy to deploy a Python project in cross-platform and cross-machine. You need spend time to prepare requirements.txt and solve the package version conflict. If project can be processed into one command, running the command can start the...
