Summary
The Old School Runescape Grand Exchange is a market where all players can place buy or sell offers for almost any item in the game. The only constraint placed on offers is a four hour buy limit that is different for each item. Another interesting feature of the Grand Exchange are the 1% tax applied to all executed sell offers.
The OSRS Wiki project maintains a useful API that, every 5 minutes, writes data about every single item trading on the Grand Exchange. The data pipeline I use to train the ML models is composed of two cronjobs that interact with the OSRSWiki API.
The baseline method I came up with is as follows: Given an item, its price spread over the last 5 mins, and its trade volume over theLast hour, compute the following variables: ROI: (selltotal - {1% tax} - buy_total) / buy total Volume ratio: (1hvolume_traded_high_price / 1h volume_tr traded_low_price) Average gold/second of item trades over last two weeks. Then do the following: Compute ROI Z score for each item. Compute
The code used to train the models can be found on my Github page. Please reach out to me if you are interested in obtaining the training data.