Explainable prediction of Qcodes for NOTAMs using column generation

TL;DR

This paper presents an interpretable multiclass classification method for predicting QCodes for NOTAMs, extending column generation techniques to improve accuracy and explainability over traditional machine learning models.

Contribution

It introduces a novel extension of column generation for multiclass text classification, addressing class imbalance and interpretability in NOTAM QCode prediction.

Findings

Outperforms SVM and neural networks in accuracy.

Provides interpretable explanations for predictions.

Reduces training time with heuristics and CP-SAT solver.

Abstract

A NOtice To AirMen (NOTAM) contains important flight route related information. To search and filter them, NOTAMs are grouped into categories called QCodes. In this paper, we develop a tool to predict, with some explanations, a Qcode for a NOTAM. We present a way to extend the interpretable binary classification using column generation proposed in Dash, Gunluk, and Wei (2018) to a multiclass text classification method. We describe the techniques used to tackle the issues related to one vs-rest classification, such as multiple outputs and class imbalances. Furthermore, we introduce some heuristics, including the use of a CP-SAT solver for the subproblems, to reduce the training time. Finally, we show that our approach compares favorably with state-of-the-art machine learning algorithms like Linear SVM and small neural networks while adding the needed interpretability component.