Intermittent demand analysis

Intermittent demand is often marked by many periods with zero demand and occasional periods with nonzero demand, making it challenging for demand planners.

In this article I examine the performance of four machine learning models—LSTM/RNN, SARIMA, XGBoost, and Croston—for estimating intermittent demand. To evaluate these models, I conducted 40 rounds of time series simulations using two patterns:

• 20 series based on a lognormal distribution (featuring numerous zeros and low-demand values with a high-dispersion right tail), and

  
  

• 20 series following a zero-inflated Poisson distribution (a very large number of zeros combined with a Poisson distribution with a small lambda).

The results indicate that analyzing the coefficient of variation (CoV) of the series is a determining factor in choosing the planning strategy (MTS/MTO).

The article "Machine Learning Algorithms for Intermittent Demand" can be accessed and downloaded for free from Academia:

Link: https://www.academia.edu/115121202/Intermittent_demand_analysis