Robust, automated financial trading and analytics with AI
With Finforge, you build, explore, and test automated trading strategies and analytics using enterprise financial data, node-based pipelines, and our AI model, Finforge-N3.
Sign up for the waitlist
In this project, S&P 500 constituents are routed through a Screener N3 model that learns to narrow the universe to maximize risk-adjusted returns. Next, a Forecast N3 model predicts prices; its signals feed Portfolio Construction and are integrated with Alpaca for live trading.
How Finforge-N3 works
Finforge-N3 is an advanced deep learning model for financial markets, designed to prevent common modelling errors like overfitting (memorising) and underfitting (not learning), while continually and quickly adapting to new market patterns and maintaining a stable long-term memory.
Meta model
Finforge-N3 uniquely combines parallel and chained deep forecasting models with reinforcement learning into a single meta-model, improving market predictions by effectively managing underfitting and overfitting.
Continual Learning
Unlike traditional pretrained LLMs like GPT, Finforge-N3 is always in learning mode, constantly adapting to market changes.
A quick learner with long memory
Learns something new every hour while maintaining long-term memory of market patterns and events.
Exogenous data
Finforge-N3 can effectively integrate many data streams like prices, news and exogenous data like oil & gold futures as market sentiment, to make a forecast for any asset.
Combine, chain Finforge-N3 and data assets for better market performance
Chain Finforge-N3 AI models with data assets in multiple steps to create entirely new kinds of trading algos and analytics that outperforms the market.
Chain Finforge-N3 models to first screen stocks monthly based on fundamentals, news, and price data -selecting up to 20 based on forecasted price. Next, shift to daily forecasts, narrowing the selection down to the top 5. Trade these selected stocks using 2x leverage via Alpaca.markets.
Forecast Oil and Gold futures with Finforge-N3, and apply these predictions as exogenous data and sentiment measures when forecasting S&P 500 stocks. Automatically rebalance a live portfolio daily, investing based on the top 3 daily forecasts.
Combine Nasdaq-100 stocks and the top 150 crypto coins by market cap, forecast their hourly intraday movements with N3, and trade using leverage on Alpaca.markets.
Dow Jones
Nasdaq
S&P 500
Forex
Commodities
Indices
Indicators
Crypto
Enterprise grade financial data
Sourcing live financial market data for AI models is hard. Finforge uses providers with servers co-located at exchanges, aligns all data in time correctly and readies it for machine learning.
Data ready for machine learning
We integrate multiple data types across asset classes, including price data, news, and financial statements for stocks, and price and news for crypto and forex markets. Finforge also have commodities, indices, futures and economic indicators
25 years of training data
Our training data extends back to the early 2000s, providing Finforge-N3 with extensive historical context spanning multiple market cycles and economic conditions.
Stock, crypto, forex and more
Our systems meticulously clean and prepare all incoming data, creating optimized datasets specifically designed for machine learning applications.
CEO & Founder
Hans Dahlström
Hans began programming at the age of 7 and, at 17, co-founded his first company, Starbreeze, which went public in 2001. In 2005, he left the game industry to co-found the B2B SaaS company Hansoft with two other partners. Hansoft was sold to Summit Partners in a significant exit in 2017, and Favro was spun out as a new startup. In 2018, Hans started studying advanced deep learning, including deep reinforcement learning and financial machine learning, alongside his work at Favro. This research led to a six-year project that culminated in the formation of SneakPeek, which entered startup formation in 2024.
hans@sneakpeek.ai
Founder
Adam Tittenberger
Adam has studied economics, statistics, and mathematics at both Stockholm University and Uppsala University. He has over 17 years of experience working at various financial institutions, including mid-sized investment firms, banks, and fintech companies. Throughout his career, Adam has held diverse roles, such as data management, portfolio risk and performance analyst, AMA operational risk analyst, credit analyst focusing on Basel/IFRS9 topics, and conducting analytical work.
adam@finforge.com
Founder
Johan Baer
Johan has extensive experience in product design, art direction, and interactive design. He has worked with various companies, including the international consultancy firm Bontouch as a Senior UI Designer, the B2B SaaS company Favro as a Lead Designer, and his own company.
johan@finforge.com
Founder
Ted Björling
Ted holds a master of science and a bachelor of business degree. He has over 20 years of senior technical leadership positions across media and entertainment, and has lead the development of several highly scalable platforms and beloved products. Most recently Ted comes from a Head of Development role at TV4, one of the largest streaming services in the Nordics.
ted@finforge.com
