Using Spark Machine Learning Models to Perform Predictive Analysis on Flight Ticket Pricing Data
This work addresses the problem of optimizing flight fare predictions for airlines or travel platforms, but it is incremental as it applies existing methods to a new dataset.
The paper tackled predicting US non-stop flight ticket prices using a large dataset of 20 million records, evaluating four regression models to identify the best real-world model based on generalization and processing times, with results measured using r2 and RMSE metrics.
This paper discusses predictive performance and processes undertaken on flight pricing data utilizing r2(r-square) and RMSE that leverages a large dataset, originally from Expedia.com, consisting of approximately 20 million records or 4.68 gigabytes. The project aims to determine the best models usable in the real world to predict airline ticket fares for non-stop flights across the US. Therefore, good generalization capability and optimized processing times are important measures for the model. We will discover key business insights utilizing feature importance and discuss the process and tools used for our analysis. Four regression machine learning algorithms were utilized: Random Forest, Gradient Boost Tree, Decision Tree, and Factorization Machines utilizing Cross Validator and Training Validator functions for assessing performance and generalization capability.