Yüksek Lisans Tezleri
Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1785
Browse
7 results
Search Results
Master Term Project Machine Learning Applications To Increase Customer Satisfaction In Finance Sector(MEF Üniversitesi, Fen Bilimleri Enstitüsü, 2019) Yiğit, Leyla; Çakar, TunaIn this project, consumers’ complaints about financial data are analyzed. After the analysis, we aim to provide a tool for financial companies such as banks, Lenders that will help them in managing communication with the consumers. Our main aim is to answer the question “How do consumers feel?” This analysis will give a complete picture of consumers’ feedback. We start the project by clustering the customers into different groups. In order to classify customers, we use classification algorithms XGBOOST and Random Forest. XGBOOST is used to predict the probability of getting a complaint. XGBOOST is also tested as an ensemble learning technique. By Using Random Forest the comparison of Bagging and Boosting is performed. This kind of model is very useful for a customer service department that wants to classify the complaints they receive from their customers. These kinds of models can also be expanded into a system that can recommend automatic solutions to future complaints as they come. The topic is motivated by the researcher’s experience in finance where she intends to increase credit sell numbers by anticipating customer feelings. The data set that we use has many measures and dimensions that facilitate to use more than 3 machine learning algorithms. The complaints database is published by the Consumer Financial Protection Bureau (https://www.consumerfinance.gov/). It provides consumers’ feedback in a string format. We also aim to analyze consumers’ complaints dataset from the perceptive of a consumer dispute.Master Term Project Carbon Price Forecasting(MEF Üniversitesi, Fen Bilimleri Enstitüsü, 2018) Karakaya, Nurhak; Ağralı, SemraIn last twenty years great improvements occurred both in technological advances and in the world economic capacity. The total production capacity of countries has been increasing rapidly. These increases need great usage of energy. For that reason, prices of energy related products are very important as they dramatically affect company budgets. Energy budgets get a great deal in total budget of companies and countries. A unit increase in an energy related product can severely affect the budget. The carbon price is one of those products. Besides carbon prices, carbon usage also affects global environment so its price also has an impact on global temperature. To forecast future carbon price different machine learning methods are used. In literature, support vector machines (SVM) [1, 2, 3], random forest (RF) [4, 5], artificial neural networks (ANN) [6, 7, 8] and Auto Regressive Moving Average (ARMA) [9] are commonly used methods. All these methods have pros and cons over the others. In this project, we also apply different machine learning methods, ANN, SVM, RF, Lasso Regression (LG)[11] and Ridge Regression (RR) [10] to forecast the carbon price over time, and give an explanation for future price movements. Then, we compare those five models by analyzing model validation methods. Finally, we choose the best model for further experiments. We have four data types: daily carbon price (CP), electricity price (EP), natural gas price (NG) and coal price (COP) that cover the period of 2009 and 2017. Prices are provided in different currencies. First of all, we work on the data to have all prices in the same currency. We completely eliminate null data. Then, graphically we investigate overall trend by smoothing the data. For analyzing data, we look for daily, monthly, yearly and seasonally time scales. For every weekday or weekends in train data set we keep a day in test data set so that we can keep the time effect in our model. After the data management process, we apply different forecasting methods to explain future carbon price tendencies.Master Term Project Sms Spam Detection in Turkish Language(MEF Üniversitesi, Fen Bilimleri Enstitüsü, 2018) Gürkan, Cem Kaya; Koç, UtkuShort message (SMS) is one of the most common communication methods. The growth of mobile phone users has led to a dramatic increase in using short messages. With the increasing number of mobile phone users, mobile phone users have started receiving unsolicited text messages. The use of SMS as a spam tool after the e-mail is due to a direct access to customer and high reversion to the users. These unsolicited short messages are disturbing the users even content intended for deceiving or defrauding (phishing). Up to date, all of the research carried out on SMS Spam detection was focused on the English language. In this study, Turkish datasets tagged with spam information is introduced and existing methods for English are applied to these datasets. The SMS dataset used in this study is gathered from different people and all messages are tagged according to whether they are spam or not. Naïve Bayes, Logistic Regression, SGD, SVM and Random Forest classification algorithms are tested with three feature extraction methods and a number of performance measures are evaluated. The evaluation resulted in a f-measure of 96.4% for SVM classification algorithm with TF-IDF (Term Frequency-Inverse Document Frequency) extraction method.Master Term Project Second-Hand Car Price Estimation Using Machine Learning(MEF Üniversitesi, Fen Bilimleri Enstitüsü, 2018) Kütükde, Şule; Özlük, ÖzgürThe ones who think to sell their cars always think about their cars’ second-hand market worth, at first. Both for the sellers and the buyers, it is crucially important to estimate the car’s realistic worth, in order not to suffer a loss of money or time. In this research, arabam.com’s advertisement data is obtained with the help of web scraping technique, and later machine learning algorithms like Linear Regression, Decision Tree, Random Forest and Gradient Boosting are applied for collected advertisement data in order to estimate cars’ prices. In addition, some hyperparameter tuning is applied for robust estimation. The models’ performances are discussed, and some remarks offered for further researches.Master Term Project Trangling Weratedogs Twitter Data To Create Interesting and Trustworthy Explosatory/Predictive Anaylses and Visulation Using Different Machine Learning Algorithms(MEF Üniversitesi, Fen Bilimleri Enstitüsü, 2018) Arı, Esra; Çakar, TunaSocial media usage has rapidly grown in recent years and knowledge in these environments increased due to this expansion. Therefore, doing exploratory and predictive analysis from intensive data of social media became so popular. However, almost all of the large datasets obtained are uncleaned / raw data. Therefore, the assessing and cleaning of the data is at least as important as the exploratory and predictive analysis. The open source WeRateDogs twitter account tweets have been gathered, assessed, cleaned, analyzed and predicted for this thesis. As a result of the study, it was understood that the most important and most time-consuming part of the predictive data analysis is the data gathering and cleaning. As a result of this project, probability of dog’s breed whether retriever or not is predicted from the tweet’s text body. 24 points increase (%34 change) in accuracy values has been achieved by doing oversampling in the data sets which contain low event observation. At the same time, the decision tree, logistic regression and random forest algorithms are compared and it is shown that the random forest's model performance is better than the others. The algorithm works 13 points better than logistic regression, 21 points better than decision tree.Master Term Project Churn Prediction in Vodafone Turkey(MEF Üniversitesi, Fen Bilimleri Enstitüsü, 2017) Genel, Gökhan; Ağralı, SemraThis Capstone Project focuses on finding a churn pattern in Vodafone postpaid consumer subscribers. The churn value refers to disconnection from subscription via port-out / Mobile number portability (MNP). It is one of the most important items that demonstrate revenue-loss. The subscriber who churned with MNP switches to a rival GSM operator. The cost of keeping an existing customer is generally cheaper than the cost of acquisition of a new customer. Focusing on customer retention is one of the most profitable strategy for growth. Statistical analysis and machine learning can help analyze churn activities and they can even alert companies when their existing customers are likely to churn. By using machine-learning algorithms, this project aims to detect Vodafone postpaid consumer subscribers who are likely to churn. This project will help the company to decrease its revenue loss.Master Term Project Development and Comparison of Prediction Models for Estimating Short Term Energy Demand of a Hotel Building(MEF Üniversitesi, Fen Bilimleri Enstitüsü, 2017) Yılmaz, Selimcan; Özlük, ÖzgürThis project presents a machine learning model building approach to developing a model for predicting next hour electricity consumption of a hotel complex in Cyprus, with the aim of improving existing prediction accuracy due to comparing different models to choose best performing. Model building process in this project includes three main steps.