Aurum AI is an autonomous financial intelligence platform engineered to monitor real-time gold markets across both COMEX Gold Futures (GC=F) and Spot Gold (XAU/USD), delivering explainable machine-learning forecasts.
Everything required to run reproducible market analysis in one platform
Prevents temporal data leakage by aligning macro series, news sentiment snapshots, and technical indicators strictly at prediction time.
Evaluates candidate models strictly against a naΓ―ve unchanged-price baseline using chronological holdouts and target-maturity gaps.
Automated publication gates ensure that an unsuccessful candidate model never automatically replaces a verified incumbent champion.
Treating COMEX Futures and Spot Gold with distinct historical pipelines
Maintains independent historical target prices, 24 technical indicators, VIX, DXY macro drivers, and archived news sentiment features to feed supervised ML regression estimators.
Tracks over-the-counter spot quotes separately from futures. Incorporates tick sample candles, range-body distributions, and dedicated RSI-and-momentum technical heuristics.
End-to-end cloud-native pipeline powering real-time gold intelligence
Aurum AI utilizes an advanced production-ready stack:
Strict boundaries ensure robust operational safety and user privacy:
Last updated: November 2026 Β· Aurum AI Final Year Project β Riphah International University, Islamabad
By accessing or using the Aurum AI platform ("Service") at auramai.netlify.app, you agree to be bound by these Terms of Service. If you do not agree, please do not use the platform.
Aurum AI is an academic and research intelligence platform developed as a Final Year Project. It provides AI-generated gold market analysis, forecasts, and macro data visualizations for informational and educational purposes only.
Nothing on this platform constitutes financial, investment, or trading advice. The forecasts generated by our machine-learning models are not guarantees of future performance. Always consult a qualified financial advisor before making investment decisions.
Market data is sourced from Yahoo Finance, TwelveData, Finnhub, FRED, and CFTC Socrata. While we strive for accuracy, we make no warranty of completeness, timeliness, or fitness for purpose. Data may be delayed or subject to provider outages.
All platform code, ML model architectures, UI designs, and content are the intellectual property of the Aurum AI team (Mir Ahmad Shah & Shahid Zaman). Reproduction or redistribution without written permission is prohibited.
The Aurum AI team and Riphah International University shall not be liable for any direct, indirect, incidental, or consequential damages arising from use of this platform, including but not limited to financial losses from reliance on forecasts.
Users agree not to: (a) attempt to reverse-engineer our ML models; (b) use automated bots to scrape data; (c) misrepresent platform forecasts as professional financial advice; or (d) violate any applicable laws or regulations.
We reserve the right to modify these Terms at any time. Continued use of the Service after changes constitutes acceptance of the updated Terms. Users will be notified via platform announcements.
Last updated: November 2026 Β· We are committed to protecting your personal data
We collect only what is necessary: email address and display name via Firebase Google/Email OAuth for account creation. We do not collect payment information, sensitive personal data, or browsing history outside the platform.
Your data is used exclusively to: (a) authenticate your session via JWT Bearer Token; (b) store your alert preferences (email opt-in for SMTP volatility alerts); and (c) personalize your Aurum AI workspace. We never sell your data.
User profiles are stored in Cloud Firestore (Google Firebase). Service credentials and API keys are isolated in GitHub Actions secrets and Cloudflare environment variables β never exposed in client bundles.
We use: Firebase Auth, Cloud Firestore (Google), Cloudflare D1/R2/Workers, Netlify CDN, Render.com (backend), Yahoo Finance, TwelveData, Finnhub, FRED, GROQ LLM. Each third party has its own privacy policy governing data they process.
If you opt in to volatility alerts, your email is used exclusively to send gold price movement alerts (|Ξ| > $100) via Gmail SMTP. You may opt out at any time from your profile settings.
We use browser local storage to persist your theme preference and session token. No third-party tracking cookies are used. Analytics are limited to anonymous Netlify page-view counts.
You have the right to: access, correct, or delete your personal data; withdraw consent for email alerts; and request data export. Contact us via the platform to exercise these rights.
For privacy concerns, reach us through auramai.netlify.app or contact the supervision team at Riphah International University, Islamabad, Pakistan.
Mir Ahmad Shah (54906)
BSCS Student
Shahid Zaman (55123)
BSCS Student
Mr. Muhammad Shabbir Hassan
Supervisor