ABSTARCT :
This paper deals with the problem of airfare prices prediction. For this purpose a set of features characterizing a typical flight is decided, supposing that these features affect the price of an air ticket. The features are applied to eight state of the art machine learning (ML) models, used to predict the air tickets prices, and the performance of the models is compared to each other. Along with the prediction accuracy of each model, this paper studies the dependency of the accuracy on the feature set used to represent an airfare. For the experiments a novel dataset consisting of 1814 data flights of the Aegean Airlines for a specific international destination (from Thessaloniki to Stuttgart) is constructed and used to train each ML model. The derived experimental results reveal that the ML models are able to handle this regression problem with almost 88% accuracy, for a certain type of flight features.
EXISTING SYTEM :
the airline corporations are using complex strategies and methods to assign airfare prices [1], [2] in a dynamic fashion. These strategies are taking into account several financial, marketing, commercial and social factors closely connected with the final airfare prices. Due to the high complexity of the pricing models applied by the airlines, it is very difficult a customer to purchase an air ticket in the lowest price, since the price changes dynamically. For this reason, several techniques [3], [4], able to provide the right time to the buyer to purchase an air ticket by predicting the airfare price, have been proposed recently. The majority of these methods are making use of sophisticated prediction models from the computational intelligence research field known as Machine Learning (ML). More precisely, Groves and Gini [4] applied PLS regression model to optimize airline ticket purchasing, with 75.3% accuracy (acc.). Papadakis [5] predicted if the price of the ticket will drop in the future, by handling the problem as a classification task using Ripple Down Rule Learner (74.5% acc.), Logistic Regression (69.9% acc.) and Linear SVM (69.4% acc.) ML models. Janssen [6] proposed a linear quantile mixed regression model to predict air ticket prices with acceptable performance for cheap tickets many days before departure. Ren, Yang and Yuan [7], studied the performance of Linear Regression (77.06% acc.), Naϊve Bayes (73.06% acc.), SoftMax Regression (76.84% acc.) and SVM (80.6% acc. for two bins) models in predicting air ticket prices.
PROPOSED SYSTEM :
The contribution of the proposed paper is summarized to the following items: (1) airfare prices prediction in Greece for the first time, (2) investigation of the features influence to the airfare prices and (3) performance analysis of the state of the art ML models in airfare prediction. The rest of this paper is organized as follows: Section II, presents some basic information regarding machine learning, and how ML can approach the problem of airfare price prediction. Section III describes the current research from a theoretical perspective and Section IV discusses the experimental approach of the used models, as well as their results. Finally, Section V concludes the overall study and points out some research directions for future work.
SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10
HARDWARE REQUIREMENTS:
Processor : Core I3
RAM Capacity : 2 GB
Hard Disk : 250 GB
Monitor : 15″ Color
Mouse : 2 or 3 Button Mouse
Key Board : Windows 08/10
