Dupely

The trust layer for online shopping

Android

iOS

E-Commerce

Visit WebsiteSee on Product Hunt

@jacob_galajda Available for Amazon Worldwide or only US?

This is so cool! I've definitely had to sort though 10 different amazon vendors with pictures that all suspiciously look the same with slightly different descriptions. It's so annoying to try and discern which products are actually identical and which may be slightly better. Gonna try this out!

Background auto-match right on the listing page is the friction-killer — manual go-check-the-app flows never survive on my phone. Since price history is ASIN-level and covers third-party sellers, does a sudden drop from a brand-new low-reputation seller get surfaced any differently than one from an established seller? Otherwise the cheapest ASIN could point me straight at the sketchy listing the trust layer is supposed to protect me from.

Hi Jacob, this one hits home. I have been fooled more than once by a price that quietly crept up right before a big sale, so knowing something has my back there feels good.

the matching accuracy question above is about honest mistakes, but is there a version where a seller games it on purpose? like stuffing a listing's title/attributes so a cheaper, lower-quality item gets matched as a "dupe" of a premium one it isn't actually equivalent to, just to ride the traffic from your recommendation. accidental mismatches you can improve with better signals, but an adversarial seller is optimizing specifically to fool whatever matching logic you publish or that people can reverse engineer from watching what gets flagged

How do you balance finding the cheapest option with ensuring shoppers still get a reliable seller and product quality?

Yeah, the unit normalization is exactly where it gets ugly. In extraction work the title and the structured pack field disagree constantly, '90ct' in the name but a 3x30 variant underneath, and whichever one you trust is wrong a surprising share of the time. What worked for us was treating price-per-unit as low-confidence unless two signals agreed (title regex plus the variant field), and just hiding the per-unit number when they didn't rather than showing a wrong one. A wrong savings figure kills trust faster than a missing one.

Building in the shopping space myself, so this one hits close. The gap between "is this product legit" and "is this seller legit" is bigger than most people realize — which one is Dupely actually scoring, or is it both? Curious which signal turns out most predictive: review-pattern anomalies or seller history. Congrats on the launch, the problem is painfully real.

The part nobody's asked about is the matching itself. Deciding two listings are the 'same product' is the whole game, and Amazon makes it ugly: a serum sold as 30ml vs 1oz, single unit vs a 2-pack, a renamed variation ASIN, a bundle with a free sample tacked on. When I worked on product matching, title plus image similarity got us to maybe 80%, and the last 20% (unit counts, pack sizes, refurb vs new) was where every wrong dupe call came from. A wrong dupe stings more than a missed one, since you're steering someone to buy the cheaper thing that isn't actually the same. How are you drawing that line today?

The Trust This Price flag using 90 days of history is the part I'd actually rely on, since fake "was $X, now $Y" drops are exactly what trips me up. When I'm on an Amazon listing with the Chrome extension, does DupeScore surface the cheaper identical product inline on the page, or do I have to open the app and search for it myself? And does the price history cover third-party marketplace sellers, or only the main buy-box?

Logan's question in this thread, whether the badge becomes the new thing to optimize around, is the one I'd push on too. I build in a category where dark patterns are the default and the honest answer is you never eliminate gaming, you price it up, so Ryan's framing rang true. What happens when a seller earns the badge legitimately and then quietly degrades, is there decay built into DupeScore?

Congrats!! Can users customize what matters most, like price history, seller trust, or return rates?

I'd love browser pop-ups explaining exactly why a seller earned or lost their credibility badge. What do you think?

This is a cool idea. How frequently is the seller trust data refreshed as new reviews and returns come in??

Congratulations on shipping. Does Dupely also compare prices across different retailers or only within marketplaces?

Congrats on the launch. I'd love notifications when a trusted seller starts offering a product I've saved. Is there a feature that exists for this?

The 90-day price history alone would save me from buying during fake "limited-time" sales. xD

As someone who shops on Amazon regularly, duplicate listings drive me absolutely crazy. Glad someone is tackling this.

Can users report products they think Dupely missed to improve future matching?