Open access
2026
A Novel Tokenization-Free GPT-2 Mechanism for Intermittent Demand Forecasting
A controlled comparative assessment within the GPT-2 family is run on 384 stratified M5 intermittent series, crossing two output-head architectures with two loss functions, showing the penalty rising monotonically with the average inter-demand interval.
Ioannis Tsantilis, Panagiotis G. Giannopoulos, Thomas K. Dasaklis et al.
· IEEE Access · 0 citations