SoylentNews is people
SoylentNews
In the online world, a number of companies use algorithms to set or suggest prices. eBay, for example, tells you what similar products have sold for and lets you choose a price based on that information. eBay’s pricing problem was relatively simple to solve: It didn’t matter where the sellers and buyers were or whether you’re selling the product today or next week. Meanwhile, over at Uber and Lyft, the ride-sharing companies, geography and time do matter—but these two companies simply set prices by decree; there is no user choice or need for transparency in how the prices are determined.
At Airbnb, we faced an unusually complex problem. Every one of the million-plus listings on our site is unique, having its own address, size, and decor. Our hosts also vary in their willingness to play concierge, cook, or tour guide. And events—some regular, like seasonal weather changes; others unusual, like large local events—muddy the waters even further.
The article is in part an advertisement for AirBnB, but there's also interesting detail there for those aspiring- or current online entrepreneurs.
(Score: 3, Informative) by skullz on Tuesday August 25 2015, @08:35PM
I think everyone else is still reading the source code (https://github.com/airbnb/airflow)
Looks like an interesting project, a mix of Java and Scala with some machine learning terms that are far newer than ones I remember. No training / testing data (always half the problem with any machine learning project) but it does seem to have the start of decent documentation.
(Score: 2) by aclarke on Wednesday August 26 2015, @01:25PM
I've thought about doing this with foreign exchange trading. There are lots of indicators that use historical data to try to give an idea of what's happening. A simple example is a moving average of the previous 10 minutes or something like that. Say there are 100 indicators, and each one has several different parameters, like the number of minutes to go back, in the moving average example. Do any of these indicators actually work? What are the correct parameters? Perhaps some are only good predictors when other indicators are in a certain position? I've done a bit of messing around with this particular idea but haven't taken it very far due to a lack of confidence that trailing market indicators really do much to tell you about anything other than the past.
I might download this code though and see if there's a way to feed it forex tick data and indicator algorithms. It would be a fun way to spend all that free time I don't have.