
Closed
Posted
Paid on delivery
Project Overview We are building a sports prediction website where users make football (soccer) predictions and write analyses. To enrich the community, we want to introduce AI-powered personas (bots) that act like real users. These bots will: • Use the SportMonks API (fixtures, advanced stats, odds) to generate probabilities for standard prediction types (1X2, Over/Under, BTTS, Correct Score, etc.). • Interpret probabilities differently based on behavioral styles (e.g. Safe Analyst, Aggressive Gambler, Trend Chaser, Underdog Hunter). • Generate longform analyses in a target language (English, German, Turkish, etc.) explaining why they made a prediction — without ever mentioning betting odds explicitly. • Post predictions & rationale on the site via browser automation (Playwright), so they behave exactly like a normal user. ⸻ Key Features • Persona Engine: Configurable personas with styles (safe, balanced, aggressive, contrarian, trend-based, etc.), posting windows, languages, and voice/tone. • Probability Engine: • Compute model probabilities using Poisson (λ from xG), Elo, and rolling form stats. • Pull SportMonks odds → normalize → blend with model probabilities (time-to-kickoff dependent). • Enforce clash rules & probability floors based on persona style. • LLM Integration (OpenAI API): Generate rationale/analysis text (strict JSON contract → safe parsing). • UI Automation: Playwright posts predictions + rationale through the website’s user interface. • Dashboard ([login to view URL] + Postgres): • Manage personas (CRUD) and their configs. • Shadow / Canary modes (draft vs live posts). • Scheduler (posting windows, quotas, blackout hours). • Runs Explorer: view each bot’s picks, probabilities (model/market/final), rationale, and status. • Basic metrics: win rate, total points, points by prediction type. • Scalable Job Queue: Redis + BullMQ workers with concurrency controls and retries. • Health/Logs: view queue depth, worker status, and failure artifacts (Playwright [login to view URL]). ⸻ Deliverables • Bot platform with all features above, deployed (Vercel + Neon Postgres + Redis worker node). • Documentation: environment variables, how to add new personas/styles, how to add new prediction types. • Codebase clean, modular, and production-ready. ⸻ Tech Stack (preferred) • Frontend/Dashboard: [login to view URL] + Tailwind • Backend/API: Node.js (TypeScript) + Prisma + Postgres • Job Queue: Redis + BullMQ • Browser Automation: Playwright • Data: SportMonks API (paid key provided) • LLM: OpenAI API ⸻ Candidate Requirements • Strong background in Node.js/TypeScript and React/Next.js. • Experience with queue systems (BullMQ, Redis, or similar). • Solid knowledge of browser automation (Playwright/Puppeteer). • Comfort working with sports data APIs (SportMonks a plus). • Understanding of probability models (Poisson, Elo) is a strong bonus. • Must deliver clean, documented, production-ready code. • Fluent English communication. ⸻ Scope & Timeline • Estimated scope: ~150 hours for first version. • Timeline: ~3–4 weeks (flexible). • Future extensions: bot learning loops, advanced analytics, multi-language support, and replay tools.
Project ID: 39726322
27 proposals
Remote project
Active 5 days ago
Set your budget and timeframe
Get paid for your work
Outline your proposal
It's free to sign up and bid on jobs
27 freelancers are bidding on average $15,524 USD for this job

I've successfully delivered similar projects using Python (Flask/Django), SQL databases, and machine learning models for accurate prediction algorithms, resulting in a 20% increase in user engagement for my last client. My expertise in web development and data science ensures a robust and engaging platform. My approach involves building a user-friendly interface using React.js, connecting to a PostgreSQL database for storing predictions and user data. Prediction algorithms, leveraging historical data and statistical models, will be implemented in Python, integrated with a Telegram bot for automated updates and notifications. Thorough testing and deployment on a secure cloud platform (AWS/Google Cloud) will ensure reliability and scalability. Ready to discuss your specific requirements? Could you share details on the desired features, particularly the scope of the prediction algorithm and the preferred level of bot integration, to ensure we craft the optimal solution?
$16,812 USD in 21 days
5.0
5.0

Hi Prasenjit S., I came across your project " Sports Prediction Website with a Bot" and I'm confident I can help you with it. About Me: I'm a agency owner with over 8+ years of experience in Node.js, API Development, Web Development. , and I understand exactly what’s needed to deliver high-quality results on time. Why Choose Me? - ✅ Expertise in required Technologies and 1 year post deployment free support - ✅ On-time delivery and excellent communication - ✅ 100% satisfaction guarantee Let’s discuss your project in more detail. I’m available to start immediately and would love to hear more about your goals. Looking forward to working with you! Best regards, Deepak
$15,000 USD in 7 days
4.6
4.6

Warm greeting!! I am an individual highly-skilled WEBSITE/API developer with more than 9 years of quality experience in designing & developing a wide range of responsive/Classified websites and Website optimization. It would be great if we can discuss further regarding the job so that we can take the next step. Moreover, If you have any query then feel free to discuss. I am available for discussion. My Specialties are as follows: *.Front End: UI/UX Designer, Graphics Design, Vue.js, React.js , Node.js, Angularjs, Nextjs, Nuxtjs HTML 5, CSS 3, Bootstrap, Javascript,Jquery, Basic Photoshop,Figma. *.Back End: Express, PHP, Laravel, Codeigniter, ZendFramework, CakePHP, Ajax, jQuery, Python,Django, ASP.NET Core. *.CMS: WordPress, Shopify, Magento, Joomla, Squarespace, Wix, PerfexCRM, Zoho. *.API Integration: APIs, Unix/Linux, and MVC Framework Architecture. *.Database: MySQL, MongoDB, MSSQL. *.Payment Gateway, PayPal , Stripe. *.SEO/Digital Marketing *Windows Desktop app development: C#, VB, C Rest I assured you about the quality work and delivery of the project on time. Response Awaiting! Regards
$10,000 USD in 7 days
4.8
4.8

Hello, I can build your sports prediction bot platform - this is a really clever approach to creating engaging community content while leveraging real statistical analysis. The combination of different persona styles with actual probability modeling will make the predictions feel authentic rather than obviously automated. I've worked with similar sports data APIs and browser automation projects before. The tricky part will be getting the probability blending right so each persona's behavior feels consistent while still being based on real statistical foundations. The LLM integration for generating natural-sounding analysis without mentioning odds explicitly is an interesting challenge too. Questions: – Do you want the bots to respond to comments or just post original predictions? – Should the probability models learn from actual match results over time or stay static initially? – Any specific leagues or competitions you want to focus on first, or cover everything SportMonks provides? I am a TOP Rated Freelancer, and you can check my reviews here as well: https://www.freelancer.com/u/kamran2012 Looking forward to working together. Thanks, Kamran
$15,000 USD in 20 days
5.7
5.7

Hello I’ve gone through your project details and I’ve worked on similar requirements in the past. I’m confident I can deliver this within your budget and timeline and less then I will create a sports prediction website where users make football (soccer) predictions and write analyses I’ve worked on similar projects before and can do this for you as well. Let’s connect in chat to discuss further and get started right away. Best regards Satyanarayan
$10,000 USD in 7 days
0.0
0.0

Hi Prasenjit S., I recently completed a very similar project. I can show u sample. Questions: 1) Probability engine: Should we use Dixon–Coles adjusted Poisson with opponent-adjusted xG (att_xG * opp_xGA/league_avg) and exponential recency decay, with league/season priors and promotion/relegation resets? How do you want market blend weights w(t) vs time-to-kickoff determined, and odds normalization via Shin vs proportional overround? Calibration KPIs: rolling log-loss/Brier/ECE targets? 2) Automation/ops: Any anti-bot controls to mimic (CSRF rotation, hCaptcha, session fingerprinting)? Should each persona maintain isolated storageState, IP/geolocation pools, realistic dwell/typing jitter and posting windows? Can we get staging creds + fixtures to capture Playwright traces and harden flows? Suggestions: 1) Establish a nightly calibration/backtest service: re-fit Poisson/Elo, learn Dixon–Coles ρ per league, isotonic regression per market/league, and optimize dynamic blend weights by minimizing rolling log-loss Derive BTTS/O/U/Correct Score from the joint score matrix; monitor Brier/ECE; version model artifacts and auto-rollback on calibration drift 2) Production rigor: enforce JSON Schema tool-calling for LLM with stats-only retrieval and a no-odds post-processor; deterministic sampling + persona templates Kindly send me a message, lets discuss in detail and my portfolio is uploaded here and on my website. Best Regards, Sid CTO and Co-Founder of Ekarthaan
$19,400 USD in 11 days
0.0
0.0

Nadia, India
Member since Feb 21, 2025
₹1500-12500 INR
$30-250 USD
$8-15 USD / hour
₹600-1500 INR
€8-30 EUR
$30-250 USD
$10-30 USD
€250-750 EUR
₹250000-500000 INR
€12-18 EUR / hour
$30-250 USD
£20-250 GBP
$250-750 USD
$10-150 USD
$10-30 USD
$2-8 USD / hour
$2-8 USD / hour
$10-30 USD
$10-50 USD
₹12500-37500 INR