An Improved Demand Forecasting Model Using Deep Learning Approach and Proposed Decision Integration Strategy for Supply Chain

Algorithm 1

The algorithm of the proposed demand forecasting system.

Given: n is the number of stores, m is the number of products, t is the number of

algorithms in the system and is an algorithm with index t. is the matrix which

includes the number of best performing algorithms for each store, and product, is the

matrix which contains the set of blacklist of algorithms for each store, and product, and

is the matrix which stores final decision of each forecast where i is the number of

stores and j is the number of products.

for i=1:n

for j=1:m

for k=1:t

if is in list then continue

else run

Calculate algorithm weight

end if

end for

for k=1:t

Choice best performing algorithms and locate in

end for

for z=1:

do scaling for

end for

Calculate proposed integration strategy, and store in

end for

end for

return all