The law of the averages or regression to the mean is a canonical law which states that most future events are likely to balance any past deviation from a presumed average.
Air force pilot trainers observed that pilots that performed amazing in their first training performed average in their second training, and pilots that performed average in their first training performed much better in their second training. This could be a classic example of regression to the means.
The same was also observed with companies. Those that showed high stock price rises in the initial years after an IPO had a more humble growth soon after — and vice versa (Malcolm Gladwell’s Outliers).
The exponential smoothing technique (EST) is used for smoothing time-series data using the exponential window function. Unlike simple moving averages which value each past observation equally, EST puts exponentially decreasing weights.