Registration is FREE. Enjoy Customizing & Monitoring the Performance of up to 5 Models & More!
A 6‑digit code was sent to
Target Ticker:
Predictors:
Indicator Periods:
Loss Function:
Fine‑tuning can take up to 3 minutes. Proceed?
Don't forget to Save Model if you make any changes!
XGBoost stands for eXtreme Gradient Boosting. "Gradient boosting" is the technique of repeatedly correcting errors, and "extreme" refers to all the clever optimizations that make it blazing fast and highly accurate – even on gigantic datasets.
Think of XGBoost as a super‑charged committee of decision trees. A single decision tree is like a flowchart: "Is the price yesterday > $100? → go left, else right." One tree is weak – it makes lots of mistakes. XGBoost builds trees one after another, and each new tree is trained to fix the errors of all previous trees combined. Over 100 or 1000 rounds, the committee becomes incredibly sharp, learning complex, non‑linear patterns that no single tree could ever capture.
Each of these knobs influences how the model learns. Tweak them to improve your forecast – or let Fine‑Tune search for the best combination.
The loss function measures how "wrong" a prediction is, and the model uses that feedback to improve. We offer two choices:
When you hit Forecast, here's what happens behind the scenes:
Every part of the model – from the predictors, the indicator periods, the hyperparameters, and even the loss function – directly impacts forecast quality.
To maximize forecast quality, we invite you to explore VIP membership with us to take full advantage of our rich database of predictors and state‑of‑the‑art fine‑tuning capabilities. We only ask for a small fee in return as training and finetuning the Models we provide for you can get quite expensive, computationally.
Thank you and if you have any questions, please feel free to email us at any time at team@stockpriceforecast.ai
XGBoost – making trees work for you since 2014 🌳
We created this project to showcase how the latest cutting-edge AI and machine learning algorithmic techniques can be trained on tabulated financial markets data to make short to medium to long-term forecasts and extract unique market insights.
These are not your vanilla off-the-shelf models. Here, you have open access to a broad array of customization options to build a bespoke solution to fit your needs. For example, you are open to curating your own custom predictor set, augment features, and choose your own hyperparameters.
Given the complexity of these techniques, training and finetuning models are computationally expensive. We encourage you to become a VIP member which will help us keep this project going, add additional AI/ML algorithms to the library, and in exchange you will gain full access to the project's features and evaluation tools that can significantly improve model performance, and more.
The pipeline between model inputs and outputs has been rigorously scrutinized and your custom inputs have direct impact on forecast performance. All that's left is for you to explore the infinite combinations of options to create and utilize your own AI / Machine Learning algorithm.
Here is a snippet of the database.
| Date | SNDK | SPY | SPX_PE | NVDA_EV_Rev | SOXX |
|---|---|---|---|---|---|
| 2026-06-05 | 74.35 | 582.41 | 21.42 | 18.73 | 452.12 |
| 2026-06-04 | 73.88 | 579.60 | 21.38 | 18.66 | 450.45 |
| 2026-06-03 | 74.10 | 581.25 | 21.44 | 18.80 | 451.67 |
| 2026-06-02 | 73.45 | 578.33 | 21.30 | 18.45 | 448.90 |
| 2026-06-01 | 72.99 | 576.12 | 21.22 | 18.30 | 446.55 |
* Data shown for illustration. Actual dataset contains many more columns.
Thank you and please feel free to reach out with any questions, requests, anything really via e‑mail: team@stockpriceforecast.ai
What is TICKER_EV_Rev (e.g. NVDA_EV_Rev)?
This is the forward Enterprise Value to forward Revenue multiple for applicable tickers in the dataset based on Consensus Wall Street estimates, calculated and updated daily.
In Top Feature Importance, what is pred_TICKER (e.g. pred_NVDA or pred_SPX)?
This is the most recent actual value of the corresponding ticker. So if we are forecasting NVDA for tomorrow, pred_SPX would be the value for SPX immediately 1 time period prior to the forecast.
What is TICKER_vol?
This is the daily US Dollar volume of the applicable ticker, calculated as the daily Volume-Weighted Average Price ("VWAP") multiplied by the Volume traded.
What is the FOMO indicator?
Measures how much recent short‑term performance deviates from a long‑term baseline, dynamically using Sharpe ratio differences when the trailing one‑year trend is positive and Z‑score differences otherwise, all computed point‑in‑time without look‑ahead.
| Anon | Free Registered | VIP | |
|---|---|---|---|
| Number of Model Predictors | 3 | 3 | Full Access (350+ and growing) |
| Forecast Length | Up to 6 Days | Up to 6 Days | Up to 63 Days (1-Quarter) |
| Lookback Period (Lag Days) | 1 to 3 Days | 1 to 3 Days | up to 69 Days |
| Feature Engineering | Max: 3 per Indicator | Max: 3 per Indicator | Max: 10 |
| Custom Hyperparameter Tuning | ✔ | ✔ | ✔ |
| Save & Load Models | 🔒 | ✔ Max: 5 | ✔ Max: 50 |
| Real-time Model Evaluation | 🔒 | ✔ Max: 5 | ✔ Max: 50 |
| State-of-the-Art Hyperparameter Fine-Tuning | 🔒 | 🔒 | ✔ |
| Early Access to New Models and Predictors | 🔒 | 🔒 | ✔ |
| Priority Model & Feature Request | 🔒 | 🔒 | ✔ |
Effective Date: June 15, 2026
Welcome to stockpriceforecasts.ai (“the Site”). By accessing or using this Site, you agree to be bound by these Terms of Use. If you do not agree, please discontinue use immediately.
All forecasts, charts, models, and data provided on the Site are for experimental and entertainment purposes only. They do not constitute financial, investment, legal, or tax advice. Nothing on this Site should be interpreted as a recommendation to buy, sell, or hold any security, derivative, or financial instrument.
While we strive to provide accurate and up‑to‑date information, we make no warranties or representations regarding the completeness, reliability, or suitability of the forecasts, data, or tools. Past performance does not guarantee future results, and all models are inherently uncertain.
You agree to use the Site solely for lawful purposes and at your own risk. You are responsible for any decisions made based on the information presented here. We strongly recommend consulting with a qualified professional before making any financial decisions.
All content, software, and algorithms on the Site are protected by copyright and other intellectual property laws. You may not copy, modify, distribute, or reverse‑engineer any part of the Site without prior written consent.
To the fullest extent permitted by law, the Site and its operators shall not be liable for any direct, indirect, incidental, consequential, or punitive damages arising from your use of or inability to use the Site, even if we have been advised of the possibility of such damages.
We reserve the right to change these Terms at any time. Continued use after changes constitutes acceptance of the new Terms.
These Terms shall be governed by the laws of the State of Delaware, without regard to conflict of law principles.
If you have any questions, contact us at team@stockpriceforecast.ai.
Last updated: June 15, 2026
The AI‑Powered Market Forecasts website (“the Site”) is a technology demonstration platform. All forecasts, predictions, backtests, and model outputs are generated by machine learning algorithms and are provided for experimental and entertainment purposes only.
The content on this Site is not intended to be, and should not be taken as, financial advice, investment recommendation, or an offer to buy/sell any security. Always do your own research and consult with a licensed financial advisor before making any investment decisions.
Forecasts rely on historical data and assumptions that may not hold in the future. Models can overfit, contain errors, and produce wildly inaccurate results. We do not guarantee the correctness, timeliness, or completeness of any data or prediction.
The Site may include data from third‑party sources (e.g., market data providers). We are not responsible for the accuracy or legality of such content.
You assume all risks associated with the use of the Site. Under no circumstances shall the Site’s owners, operators, or affiliates be liable for any loss or damage resulting from reliance on the information provided.
This platform is an experiment in applying machine learning to financial time series. Results are for curiosity, education, and entertainment, and should never be the sole basis for real‑world trading or investment decisions.
For questions or concerns, email team@stockpriceforecast.ai.
Effective Date: June 15, 2026
AI-Powered Market Forecasts (“we”, “us”, or “our”) respects your privacy. This Privacy Policy explains how we collect, use, and protect your personal information when you use our website.
Account Information: When you register, we collect your email address and a hashed password. We do not collect your name or other identifying details unless you voluntarily provide them.
Usage Data: We use Google Analytics to collect anonymised data about your interaction with the Site (pages visited, time spent, browser type, etc.). This data may include your IP address but is not linked to your account.
Cookies: We use cookies to maintain your login session and to remember your preferences (e.g., EMA overlays). You can disable cookies in your browser, but some features may not function properly.
We do not sell, rent, or trade your personal information. We may share data with trusted third‑party service providers (e.g., Stripe for payments, Google for analytics) who are bound by confidentiality agreements. We may also disclose data if required by law.
We implement reasonable technical and organisational measures to protect your data. However, no method of transmission over the Internet is 100% secure, and we cannot guarantee absolute security.
Depending on your jurisdiction, you may have rights to access, correct, delete, or restrict the processing of your personal data. To exercise these rights, please contact us at team@stockpriceforecast.ai.
The Site is not intended for individuals under the age of 18. We do not knowingly collect data from children.
We may update this Privacy Policy from time to time. The date at the top indicates the last revision. Your continued use of the Site after changes constitutes acceptance.
For any privacy‑related inquiries, email us at team@stockpriceforecast.ai.