id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_rh2ldlogbze5dldx4ce5fsu4ee	Philip Hans Franses	Combining SKU-level sales forecasts from models and experts	2011	19	.pdf	application/pdf	5482	434	73	Correlating the weights of the expert forecasts in these linear combinations with the model forecasts gives most weight of the expert forecast. And, if so, is that robust across forecast horizons and does it differ across experts? Our data concern a firm that creates model forecasts and which has almost fifty experts no information on what exactly drives the expert to deviate from model forecasts and also not This combined forecast for each expert i given a horizon h is given by where we compute the value of ai across all products within an expert-horizon combination. of the cases model forecasts combined with expert forecasts yield improvement. When we computed the optimal weights of combining model forecasts and expert the degree of wrong-signed expert forecasts, and the degree of no deviation from the model combine model forecasts and expert forecasts. Table 4: Optimal weights in the combined forecast, that is,	./cache/work_rh2ldlogbze5dldx4ce5fsu4ee.pdf	./txt/work_rh2ldlogbze5dldx4ce5fsu4ee.txt