Abstract: A method of training a neural network to approximate a forecasting error of a passenger-demand forecasting model that includes calculating, using the forecasting model, a historical passenger demand forecast for each key level in a set of key levels and for each departure date in a set of historical departures dates; applying a dropout model to the historical passenger demand forecasts to create a training sample; training, using the historical passenger demand forecasts and the training sample, the neural network, to approximate forecasting errors associated with the forecasting model; calculating, using the forecasting model, a future passenger demand forecast for each key level in the set of key levels and for each departure date in a set of future dates; and approximating, using the trained neural network, the forecasting error associated with the future passenger demand forecasts for the second set of departure dates.

Abstract: The blanket is designed to adjust in dimension and performance, permitting a user to use the blanket in a multitude of situations. The body of the blanket has a head opening and a series of complementary zippers attached to the blanket. Complementary zipper halves are attached to the left and right edges of the blanket body, permitting the right and left edges of the blanket to be attached together or for other blankets of the invention to be attached, forming a larger blanket. Another complementary zipper set includes zipper halves attached to the bottom edge of the blanket and about one third up the blanket to allow shortening of the blanket length. A plurality of foot pockets are placed on the lower portion of the blanket. The blanket may also be folded up into a bag and carried using a strap.