Abstract

Travelling through flights has become an integral part of today’s lifestyle as more and more people are opting for faster travelling options. The flight ticket prices increase or decrease every now and then depending on various factors like timing of the flights, destination, duration of flights. various occasions such as vacations or festive season. Therefore, having some basic idea of the flight fares before planning the trip will surely help many people save money and time. In the proposed system a predictive model will be created by applying machine learning algorithms to the collected historical data of flights. This system will give people the idea about the trends that prices follow and also provide a predicted price value which they can refer to before booking their flight tickets to save money. This kind of system or service can be provided to the customers by flight booking companies which will help the customers to book their tickets accordingly.

 INTRODUCTION

This project aims to develop an application which will predict the flight prices for various flights using machine learning model. The user will get the predicted values and with its reference the user can decide to book their tickets accordingly. In the current day scenario flight companies try to manipulate the flight ticket prices to maximize their profits. There are many people who travel regularly through flights and so they have an idea about the best time to book cheap tickets. But there are also many people who are inexperienced in booking tickets and end up falling in discount traps made by the companies where actually they end up spending more than they should have. The proposed system can help save millions of rupees of customers by proving them the information to book tickets at the right time. The proposed problem statement is “Flight Fare prediction system”. II. RELATED WORK Proposed study[1] Airfare price prediction using machine learning techniques, For the research work a dataset consisting of 1814 data flights of the Aegean Airlines was collected and used to train machine learning model. Different number of features were used to train model various to showcase how selection of features can change accuracy of model. In case study[2] by William groves an agent is introduced which is able to optimize purchase timing on behalf of customers. Partial least square regression technique is used to build a model. In a survey paper [4] by supriya rajankar a survey on flight fare prediction using machine learning algorithm uses small dataset consisting of flights between Delhi and Bombay. Algorithms such as K-nearest neighbours (KNN), linear regression, support vector machine (SVM) are applied. Research done by Santos[3] analysis is done on air fare routes from Madrid to London, Frankfurt, New York and Paris over course of few months. The model provides the accepted number of days before buying the flight ticket. Tianyi wang[5] proposed framework where two databases are combined together with macroeconomic data and machine learning algorithms such as support vector machine, XGBoost are used to model the average ticket price based on source and destination pairs. The framework achieves a high prediction accuracy 0.869 with the adjusted R squared performance metrics In[6] the research a desired model is implemented using the Linear Quantile Blended Regression methodology for San Francisco–New York course where each day airfares are given by online website. Two features such as number of days for departure and whether departure is on weekend or weekday are considered to develop the model. 

IMPLEMENTATION

For this project, we have implemented the machine learning life cycle to create a basic web application which will predict the flight prices by applying machine learning algorithm to historical flight data using python libraries like Pandas, NumPy, Matplotlib, seaborn and sklearn. . Our dataset consists of more than 10,000 records of data related to flights and its prices. Some of the features of the dataset are source, destination, departure date, departure time, number of stops, arrival time, prices and few more. In the exploratory data analysis step, we cleaned the dataset by removing the duplicate values and null values. If these values are not removed it would affect the accuracy of the model. We gained further information such as distribution of data. Next step is data pre-processing where we observed that most of the data was present in string format. Data from each feature is extracted such as day and month is extracted from date of journey in integer format, hours and minutes is extracted from departure time. Features such as source and destination needed to be converted into values as they were of categorical type. For this One hot-encoding and label encoding techniques are used to convert categorical values to model identifiable values. Feature selection step is involved in selecting important features that are more correlated to the price. There are some features such as extra information and route which are unnecessary features which may affect the accuracy of the model and therefore, they need to be removed before getting our model ready for prediction. After selecting the features which are more correlated to price the next step involves applying machine algorithm and creating a model. As our dataset consist of labelled data, we will be using supervised machine learning algorithms also in supervised we will be using regression algorithms as our dataset contains continuous values in the features. Regression models are used to describe relationship between dependent and independent variables. The machine learning algorithms that we will be using in our project are

Linear Regression

In simple linear regression there is only one independent and dependent feature but as our dataset consists of many independent features on which the price may depend upon, we will be using multiple linear regression which estimates relationship between two or more independent variables and one dependent variable. The multiple linear regression model is represented by: Y = β0x1+…. +βnxn + Ɛ Y = the predicted value of the dependent variable Xn = the independent variables βn = independent variables coefficients Ɛ = y-intercept when all other parameters are 0 Decision Tree Decision trees are basically of two types classification and regression tree where classification is used for categorical values and regression is used for continuous values. Decision tree chooses independent variable from dataset as decision nodes for decision making. It divides the whole dataset in different sub-section and when test data is passed to the model the output is decided by checking the section to which the datapoint belong to. And to whichever section the data point belongs to the decision tree will give output as the average value of all the datapoints in the sub-section Random Forest Random Forest is an ensemble learning technique where training model uses multiple learning algorithms and then combine individual results to get a final predicted result. Under ensemble learning random forest falls into bagging category where random number of features and records will be selected and passed to the group of models. Random forest basically uses group of decision trees as group of models. Random amount of data is passed to decision trees and each decision tree predicts values according to the dataset given to it. From the predictions made by the decision trees the average value of the predicted values if considered as the output of the random forest model.

CONCLUSION

A proper implementation of this project can result in saving money of inexperienced people by providing them the information related to trends that flight prices follow and also give them a predicted value of the price which they use to decide whether to book ticket now or later. In conclusion this type of service can be implemented with good accuracy of prediction. As the predicted value is not fully accurate there is huge scope for improvement of these kind of service. 

best cse final year projects
best cse projects
best cse engineering projects
best projects for cse engineering students
best project for computer science engineering
what are the best projects for cse btech
what are the projects for cse
top 10 projects for cse students
best iot projects for cse students
best cse projects for final year
good projects for computer science engineering students
best projects for cse students
best projects for computer engineering students
best projects for computer science students
best domain for cse final year projects
best final year projects for cse 2020
best projects for cse final year students
best btech cse final year projects
best cse projects
best cse project ideas
best cse project topics
best domain for cse project
which domain is best for doing project in cse
best btech projects for cse
best final year projects for cse
Mifratech websites : https://www.mifratech.com/public/
Mifratech facebook : https://www.facebook.com/mifratech.lab
mifratech instagram : https://www.instagram.com/mifratech/
mifratech twitter account : https://twitter.com/mifratech