What exactly high throughput means in the Data Science field as I'm learning Data Engineering I have encountered it so many times but I didn't know the exact meaning of it. Can someone break that word into simple words so I could relate it.
Throughput is typically measured in terms of data records (or bytes) processed per second. It is often reported in combination with latency, which measures the time needed to perform that processing.
For example, after the Singles Day Shopping Festival in China on Nov 11, 2020, Alibaba reported having processed as many as four billion events per second -- which we might call their peak throughput.