Shortage of a product

Introduction

This was a project that was followed with the CRISP-DM data mining methodology.

The data that could satisfy the business questions were first identified. Once obtained, an empirical cumulative distribution of the evaluated variables was constructed.

Subsequently, the construction of an interpolation function was made that will be used for a group of x Monte Carlo simulations and thus obtain the probability of occurrence of each simulation.

Subsequently, the construction of an interpolation function was made that will be used in the Monte Carlo simulations that are done in the subsequent step.
These simulations follow a normal distribution of the correlations of the variables evaluated from the historical values obtained in the database. FThen, through the interpolation function, obtain the simulated values.

Finally, Starting from the simulated values, the probability of occurrence of the low ending inventory was determined.

Once the model was evaluated and the results were validated, this process was automatized.

Tools: SQL Management Studio, Anaconda, Jupyter Notebook, GIT, Azure Devops
Languajes: SQL,Python
Python Libraries: Pandas, Numpy,Scipy,statsmodels