Hacker News Reader

Comment by benvanderbeek | Hacker News Reader

I work at a mid sized Amazon 3rd party seller. We reprice automatically. With thousands of SKU's there's no other way to be competitive. There are many layers to consider though, you definitely can't let your whole catalog auto-reprice. Usually sellers just focus on their top X% SKU's and let the rest auto-calculate.

I wonder if we have a price ceiling setup...?

Edit: Yes we have a floor and ceiling. I have no idea what I was thinking.

View on HN

Any 3rd party tools available to 3rd party sellers? Offering something that beats the current algorithms could be a good deal (if its not illegal).

I have code that does ecommerce price point optimization using machine learning. In an ideal setting, it combines a variety of signals, including prediction using previous sales data. It's also able to "smooth" over different products, so that you can make good price point choices even for products that have very little sales history.

What's the algorithm?

Edit: I'm puzzled by the downvotes to my honest question. "machine learning" is not an algorithm, it's a field!

Probably some sort of regression for the prediction part, and perhaps linear programming for the price optimization, since there are probably some nontrivial (but possibly linear?) constraints on pricing.

What would be even more useful is to have the browsing customer's data passed in as a signal as well, but I'm guessing Amazon doesn't send that out to third parties. If 3rd parties could also customize their prices based on the potential of someone to buy (and perhaps offer bundled items based on their own algorithms) we'd probably see even greater efficiencies than we've already seen.

Yep they exist. Sellers are pretty hesitant to say who they use since that is handing business intelligence to their competitors.

You can access your seller account programatically using the existing MWS APIs

https://developer.amazonservices.com/

Reply on news.ycombinator.com