This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
SigPath
Long, short or hold – read from the shape of price paths
SigPath gives a long, short or hold call with entry, stop-loss and take-profit for 17 crypto, forex and gold markets. Built on path signatures + ridge regression, re-fitted and tested out-of-sample on every run. No edge? It says hold.
I'm Marco, and I built SigPath because most "signal" tools either hide their method or promise 85 % win rates nobody can check.
What it does: pick a market (BTC, ETH, SOL, EUR/USD, gold and 12 more) and a timeframe (15m to 1d). SigPath returns long, short or hold – with entry, stop-loss (1.5× ATR) and take-profit (2.5× ATR).
How it works: the last 24 candles are turned into a path and summarised by its signature – a set of iterated integrals from rough path theory that captures not just how far price moved, but in which order and how much it zig-zagged. A ridge regression learns from up to 1,500 past windows, and every single run is walk-forward tested on data the model hasn't seen. If the out-of-sample check shows no edge, you get "hold" – which honestly happens a lot.
What's free:
– 1 free analysis per account
– Free calculators (ATR stop-loss with live ATR, position size, risk/reward), no sign-up
No comment highlights available yet. Please check back later!
About SigPath on Product Hunt
“Long, short or hold – read from the shape of price paths”
SigPath was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #476 on the daily leaderboard. SigPath gives a long, short or hold call with entry, stop-loss and take-profit for 17 crypto, forex and gold markets. Built on path signatures + ridge regression, re-fitted and tested out-of-sample on every run. No edge? It says hold.
SigPath was featured in Fintech (47.8k followers), Investing (26.9k followers) and Cryptocurrency (5.7k followers) on Product Hunt. Together, these topics include over 34.3k products, making this a competitive space to launch in.
Who hunted SigPath?
SigPath was hunted by Pommes. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how SigPath stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Hey Product Hunt 👋
I'm Marco, and I built SigPath because most "signal" tools either hide their method or promise 85 % win rates nobody can check.
What it does: pick a market (BTC, ETH, SOL, EUR/USD, gold and 12 more) and a timeframe (15m to 1d). SigPath returns long, short or hold – with entry, stop-loss (1.5× ATR) and take-profit (2.5× ATR).
How it works: the last 24 candles are turned into a path and summarised by its signature – a set of iterated integrals from rough path theory that captures not just how far price moved, but in which order and how much it zig-zagged. A ridge regression learns from up to 1,500 past windows, and every single run is walk-forward tested on data the model hasn't seen. If the out-of-sample check shows no edge, you get "hold" – which honestly happens a lot.
What's free:
– 1 free analysis per account
– Free calculators (ATR stop-loss with live ATR, position size, risk/reward), no sign-up
– A full write-up of the method, including where it fails: sigpath.app/learn/path-signatures-trading
I'd love feedback on two things: is the out-of-sample info shown with each signal useful to you, and which markets should come next?
(Not investment advice – it's a statistical model, treat it like one.)