AI-Based Stock Sentiment and Recommendation Tool

@starttechno

I’d start by mapping the existing MySQL news rows and creating an idempotent n8n workflow that processes only new or updated articles. A small Python service would normalize entities, ask GPT-4o-mini for structured sentiment, event impact, confidence, and rationale, then store the result and Buy/Hold/Sell signal in MySQL with an Excel export. The score can combine sentiment, market-impact level, source confidence, recency decay, and agreement across articles, with configurable thresholds rather than hidden rules. I recommend Finnhub or Alpha Vantage for ticker/company validation and enrichment, while keeping your current news database as the primary input. I previously fixed a live trading platform’s frozen price charts by adding Twelve Data caching, credit budgeting, and last-good-price fallback. You will receive the working n8n/Python pipeline, database tables, scoring configuration, concise explanations, and Excel output in 2 days. Is the existing MySQL news table already linked to ticker symbols, or would that mapping also be needed? Muhammad Saad

@sajjadtaghvaeifr

Hello, I trust you're doing well. I am well experienced in machine learning algorithms, with nearly a decade of hands-on practice. My expertise lies in developing various artificial intelligence algorithms, including the one you require, using Python, and similar tools. I have worked with pytorch, and tensorflow to develop DL models, .I hold a doctorate from Tohoku University and have a number of publications in the same subject. My portfolio, which showcases my past work, is available for your review. Your project piqued my interest, and I would be delighted to be part of it. Let's connect to discuss in detail. Warm regards. please check my portfolio link: https://www.freelancer.com/u/sajjadtaghvaeifr

@Prutheus

News already collected in MySQL, needing sentiment plus a Buy, Hold or Sell signal. One thing worth agreeing upfront: a sentiment score alone is a weak signal, so the value is in how sentiment is aggregated per ticker over time and combined with volume of coverage. How I would build it: - Sentiment per article with an LLM, scored per mentioned ticker rather than per article, since one article often covers several - Aggregation per ticker over a rolling window, weighted by source and recency, which is what turns noisy article scores into something stable - Signal derived from the aggregate with explicit thresholds, and every signal traceable to the articles behind it - Runs on a schedule against your existing MySQL, results written back so your current system just reads a new table I run LLM pipelines in production for industrial clients, 24/7, including document and text classification at volume. One honest note: this produces a signal, not investment advice, and should be labelled that way. One question: how many articles per day? Martin

@devendrathakur12

Automating stock sentiment and recommendations is straightforward work for me — I’d connect your existing MySQL news tables to n8n, use Python workers for scoring, and store structured sentiment, impact, signals, confidence, and explanations back into MySQL. I’d use an LLM such as GPT-5.6 for event interpretation, with FinBERT or a smaller finance-tuned model as a second signal, then combine sentiment, event impact, recency decay, source reliability, and historical price reaction into a documented score rather than letting the LLM directly decide Buy/Hold/Sell. A likely failure symptom is repeated news producing conflicting signals for the same ticker; I’d add deduplication using normalized headlines plus timestamps and source IDs. Share your MySQL schema and current n8n/workflow files, and I can start immediately.

@durgesh8527

As an experienced full-stack developer specializing in AI and automation, I believe I am the perfect fit for your project. With my extensive command of technologies like OpenAI, Django, and Gemini, combined with my ability to build clean and robust code, I can design a scalable and reliable system for sentiment analysis and stock recommendations. My skills in API development, database programming, and cloud management will ensure smooth data integration, efficient storage, and precise analysis of news in your MySQL database. Utilizing tools like NLP and OCR as well as expertise in financial data analysis will generate accurate trading signals. Speaking of reliability, your project's success relies heavily on choosing the right kind of news and data APIs. I'm well-versed in different options such as Eikon Data API or NewsOne API that ensure good quality financial news and downtimes are kept at a minimum. Additionally, my knowledge of different databases including MongoDB, Elasticsearch and Redis makes me a versatile option that can adapt to differences in focused architecture.

@denisSolution

Hi, I'm Denis, a full-stack developer specializing in automated analysis systems combining data collection, AI processing, and structured storage. I've built sentiment analysis pipelines and recommendation engines handling real-time data. I understand your project: stock news flows into MySQL, and you need an automated pipeline that analyzes sentiment, evaluates market impact, and generates buy/hold/sell signals with reasoning. For architecture, I'd use n8n for orchestration—it handles scheduling, error recovery, and data flow naturally. The workflow pulls news from MySQL, sends batches to an LLM for sentiment and impact analysis, calculates weighted recommendation scores based on sentiment strength and recency, then stores results in MySQL and exports to Excel. I'd recommend Claude or GPT-4 for analysis. Claude handles financial context well and is cost-effective for batch processing. I'd structure prompts to extract sentiment polarity, confidence scores, and risk factors in consistent JSON format feeding directly into your scoring logic. The sentiment score combines LLM confidence ratings with keyword intensity and temporal decay. Recommendations weight recent high-confidence signals more heavily, with clear buy/hold/sell thresholds. Each record stores the news summary, sentiment breakdown, and triggering factors. Key consideration: ensuring LLM output consistency at scale. I'd build validation and retry logic into n8n so malformed responses get reprocessed rather tha

@PINESCRIPTERR

Hi, I understand you already have a MySQL system collecting stock news and want to turn that data into a reliable AI-driven sentiment and market-impact analysis pipeline with structured, explainable signals. I can build the workflow around n8n or a Python service, connecting your existing MySQL database to an analysis layer that processes each news item, identifies the affected company/ticker, evaluates sentiment and potential market impact, and aggregates multiple events into a configurable stock-level score. The recommendation engine can then produce Buy/Hold/Sell signals or a clearly defined numerical scoring system, with each result linked to the major news and factors influencing it. For the stack, I’d consider n8n for orchestration, Python for scoring/aggregation logic, MySQL for persistent results and an LLM such as GPT-class or Claude models for contextual analysis. News enrichment can use sources such as Finnhub, Alpha Vantage, Polygon or another provider depending on your required coverage, licensing and existing data. I’ll separate sentiment, event impact, confidence and aggregation so the scoring methodology remains transparent and adjustable rather than relying on an opaque LLM-generated recommendation. Results can be written back to MySQL and/or exported to Excel, with logging, retries, duplicate handling and monitoring for reliability. I can provide relevant technical details or examples . Best regards, Houssame

@krupnovdenis

Hello! We can build a reliable AI-based stock sentiment and recommendation system for this task. 1. Which data sources or news APIs are already in use? 2. Do you prefer the results to be saved in MySQL, Excel, or both? — About us We are dZENcode – a full-cycle IT company for digital product development: from design and programming to integrations and post-release support. We build projects from scratch and also work on existing solutions that need further development, improvements, or technical support. You can find detailed information about our services and rates on our official website: https://dzencode.com. Please review it – after that, we can discuss the details and agree on the next step. ⚠️ After clarifying all details, we will define the scope, the suitable cooperation format – task-based, outsourcing, or outstaffing – and the final cost. Projects are guaranteed to reach release with us: • 10+ years providing IT services; • 90+ in-house specialists; • 250+ public reviews since 2015; • We support products under SLA after launch; • We work under NDA and a company contract!

@billybryan98

Hello there. I hope you are donig well. I have successfully developed AI-driven sentiment analysis and recommendation systems in the financial sector. My expertise in Python and PHP, combined with my experience in machine learning, positions me to create a reliable tool that meets your project's requirements and exceeds expectations. I understand that you need an automated system to analyze stock news sentiment and generate actionable recommendations. I will utilize advanced sentiment analysis techniques and a robust recommendation engine to produce insights based on the data from your MySQL database, ensuring clarity and accuracy in each recommendation. I will deliver a high-quality, extensible solution that integrates seamlessly with your existing architecture. My approach includes a well-thought-out technology stack, utilizing efficient APIs for data gathering and a powerful LLM to enhance sentiment evaluation, ensuring reliable performance tailored to your needs. Please feel free to reach out to me. I look forward to working with you. Best regards, Billy Bryan

@AndrewJSMAN

I've built similar systems using Python, FastAPI, and MySQL for financial data pipelines, so this is right in my wheelhouse. I'll set up a modular pipeline with Python for sentiment analysis (VADER or FinBERT) and recommendation scoring, then integrate it with your MySQL database via SQLAlchemy. For news/data APIs, I'll use Alpha Vantage and NewsAPI for real-time feeds, with fallback to your existing dataset. I'll deploy the LLM (Mistral or Llama 3) for contextual analysis, scoring sentiment on a -1 to +1 scale and recommendations on a 0-100 confidence metric. Results will be stored in MySQL tables with timestamps and metadata. I can start immediately. Thanks, Andrii.

@arslanshahid386

Hi, I see you're looking to automate sentiment analysis and stock recommendations using AI with your existing MySQL database. Leveraging my expertise in PHP, I can integrate AI tools that will analyze stock news sentiment and assess market impacts effectively. By using machine learning libraries, I can build a recommendation engine that generates precise Buy/Hold/Sell signals, enhancing decision-making capabilities. Could you share more about the specific agentic tools you're considering, or would you like recommendations on the best options available?

@longngoc2307

==== Hi - Truong here ==== "AI STOCK SENTIMENT & RECOMMENDATION ENGINE" — you already have the news in MySQL; the missing piece is reliable scoring, explanations, and stored signals. I’d build this as a small Python pipeline: read new news from MySQL, score sentiment + market impact with an LLM, combine those scores with simple rules into Buy/Hold/Sell signals, then save the result back to MySQL or Excel. This keeps the logic easy to adjust instead of locking everything inside one prompt. For reliability, I’d also store the news used, sentiment score, impact score, final recommendation, and explanation for each stock so you can trace why a signal was produced. AI-assisted development and existing libraries make this practical without overbuilding the first version. Which MySQL table/fields currently contain the stock symbol, news title, article text, and publication time? Looking forward to work with you.

@lazarr4

Hello, I can build a reliable AI sentiment and recommendation system using a modular architecture that separates data collection, analysis, and reporting. I’ve built a similar n8n-based stock analysis tool for a client, where I combined news APIs with a custom sentiment scoring model to generate buy/sell signals—reducing manual analysis time by 60%. I’d approach this by structuring the system as three layers: data ingestion (news APIs), sentiment/recommendation engine (LLM + scoring logic), and output (Excel/MySQL). For the LLM, I’d use Mistral or Llama 3 for cost efficiency while ensuring high accuracy. The recommendation score would combine sentiment polarity (positive/negative) with market impact metrics like volume and historical trends. Proper implementation will give you actionable insights faster, reducing the time spent manually analyzing news. I’ll also include a validation step to ensure the system’s recommendations align with historical market movements. Once the project is done, I’ll walk through the results with you to confirm the system’s reliability before handing it over. If this approach works for you, I’d be happy to discuss the details further. Thanks, Lazar.

@carlosd178

Hello, After reviewing your project requirements, I understand that you need an AI-powered sentiment analysis and recommendation system connected to your existing MySQL stock news database. My proposed approach would be: • Python-based backend for data processing and automation • LLM integration for news understanding and sentiment analysis • Sentiment scoring + rule-based/ML recommendation logic for Buy/Hold/Sell signals • MySQL storage layer for historical analysis and future improvements For LLM selection, I would choose a model based on accuracy, cost, and API reliability. I would also evaluate financial news APIs such as Alpha Vantage, Finnhub, NewsAPI, or other market-focused sources depending on your requirements. The main challenge is not just connecting APIs, but creating a consistent scoring system where each recommendation has clear reasoning based on news events and sentiment factors. I have a couple of quick questions: • Do you already have the stock news database schema and historical data available? • Should the recommendation engine focus on short-term trading signals or longer-term investment analysis? I would be glad to discuss further details and am ready to start immediately. Best regards, Carlos.

@melopgabriel

Hi, this is exactly the kind of system that needs more than API wiring: you want reliable stock sentiment, a clear recommendation engine, and results stored cleanly in MySQL or Excel. I’ve built automation and data workflows with n8n, Python, and LLM-based analysis, including pipelines that collect content, score it, and write structured outputs for reporting and downstream use. My approach would be to ingest news from your existing MySQL source, enrich each item with entity detection and sentiment analysis, then aggregate signals by ticker into a transparent Buy / Hold / Sell score. I’d keep the logic extensible, with a rules layer plus LLM reasoning for concise explanations. For the stack, I’d use n8n for orchestration, Python for scoring, MySQL for storage, and OpenAI or Claude for analysis depending on cost and latency needs. If you’d like, I can outline the architecture and scoring model in detail. Best regards, Gabriel

@cliftonc20

Hi, Your system’s goal to automate stock sentiment analysis and generate actionable recommendations from news aligns well with my experience building AI-driven forecasting and document intelligence platforms. The main technical risk is ensuring reliable ingestion and accurate sentiment extraction from noisy financial news data, which directly impacts recommendation quality. I’ve led Dent-Cloud, a scalable AI forecasting platform processing high-frequency financial time-series data in MySQL, and DocIntel AI, which automates document ingestion and AI event extraction with structured storage and retrieval. Both projects required robust pipelines for data ingestion, analysis, and reliable output. I typically design these systems by separating ingestion, sentiment analysis, recommendation scoring, and storage layers to isolate failures and scale components independently. Early validation of sentiment accuracy and recommendation logic is critical. For reliability, I implement confidence thresholds, fallback routing to simpler heuristics, and continuous monitoring to maintain stable production performance. I can start by outlining a scalable ingestion and recommendation architecture tailored to your existing MySQL data and desired output format. Clifton

@Jennycreation

Hello Sir, I have already worked on similar types of website and software development projects and I am confident that I can successfully handle your project. I am a full-time freelancer with **17+ years of experience** in web development, software development, automation, and API integrations. My expertise includes: * ASP.NET C# web and software development * Android app development * Python automation and web scraping (Amazon, Instagram, Facebook, Google Maps, LinkedIn, Telegram, and other custom scraping solutions) * JavaScript, jQuery, AJAX, Bootstrap, HTML5 * Microsoft SQL Server database development * Payment gateway integration * SMS, Email, Banking, Financial, and Insurance API integration * Custom automation bots and workflow automation software I focus on delivering **high-quality, scalable, and reliable solutions** with clean code and long-term support. Please contact me in private chat so we can discuss your requirements in detail. I can also show you a **demo of similar projects** I have completed. Looking forward to working with you. Thanks & Regards

@codeandcommand

Pulling sentiment straight from your existing MySQL news table is the right move, no need to touch your data collection. I would run a Python NLP pipeline, FinBERT or VADER tuned for financial text, to score each article, then generate buy or hold recommendations per ticker. Working version in 5 days, can start today. The bid and timeline reflect the post as written, we will firm both up after a scope call. I can run a quick free demo scoring a sample of your stored articles first.

@manishashree12

Hello there, I understand you need an AI-based stock sentiment and recommendation tool that automates sentiment analysis and generates actionable insights. My approach would involve leveraging machine learning models for sentiment analysis and implementing a recommendation engine based on collected data. I have experience working on similar sentiment analysis and recommendation system projects, ensuring reliable and extensible solutions. For the architecture, I propose using Python with TensorFlow for ML models, integrating news/data APIs like Bloomberg or Alpha Vantage, and utilizing BERT for sentiment analysis due to its contextual understanding. The sentiment/recommendation score calculation would be based on a weighted analysis of news events and sentiment factors. Looking forward to discussing this further with you. Thanks, Manisha