Time series data is data that has been indexed, listed, or graphed in time order. For example, the daily closing value of the NASDAQ, the heart rate of a person measured at hourly intervals, a single step in a simulation run, or an individual frame in a video.
Time series data is commonly used for natural language processing, video processing, robot control, financial forecasting, and in medical diagnostics.
Time series data processing is critical to understanding our environments, which exist not only in space but in time, as well. “The real world is all about sequences. Even our perception — you’re not perceiving images, you’re perceiving sequences of images,” says MIT’s Ramin Hasini. “So, time series data actually create our reality.”
Using Time Series Data
Analyzing this data in real time, by connecting streaming sources in HASH, allows for future behavior to be anticipated — useful in and of itself, as well as providing a basis for more accurate agent-based simulation.
Time series data often has internal structures that can be analyzed (such as a tendency to autocorrelate, as well as trend or seasonal variation).