Within last week only I’ve encountered two interesting (and very similar) design cases (two different projects, two different teams): System will be spammed with a constant stream of simple data messages in coherent format. Each data sample will contain few simple metrics (mainly currency, price and quantity). Project team will have to propose a solution that is able to detect suspicious cases (like: new order for given currency has got the price that is more than 20% higher than average price for last hour). Their plan is to record data in SQL and perform suitable queries in pre-set time…