Yüksek Lisans Tezleri
Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1785
Browse
64 results
Search Results
Master Term Project Segmentation With Unsupervised Learning: an Application Using the Walker's Data(MEF Üniversitesi Fen Bilimleri Enstitüsü, 2021) Polat, Taylan; Özgür ÖzlükIn this project, the Walkers suitable for the service were filtered by using the dataset shared by the DogGo company. Then, unsupervised machine learning methods such as K-Means, Gaussian, Principal Component Analysis were used to score and cluster the most suitable walkers according to performance, willingness, and experience.DogGo is the first mobile application in Turkey that provides pet walking and grooming services to its customers in a safe and professional manner. DogGo provides a professional service where dogs are taken care of in dog families' own homes or at the caretaker's home for any need of dog families. DogGo Company wants to provide the best matching of walkers and animals, using Machine Learning algorithms, through a 5-step acquisition process for their walkers.While the results of the K-means models created on the unique sliders were compared with the help of the Elbow method and the Silhouette score, the results of the Gaussian models were compared with the AIC and BIC method. In addition, an RFM scoring in a classical structure has also been created. When the results of the study were examined considering the Elbow and Silhouette scores, it was shown that the model created with K-Means gave the best results, and the number of clusters was decided as 2.Master Term Project Game Recommendation System for Steam Platform(MEF Üniversitesi Fen Bilimleri Enstitüsü, 2021) Bayram, Serhan; Semra AğralıIncreasing number of choices and competition in the markets, force companies to differ in services they provide to their customers. Offering better services have a positive impact on customer loyalty, and to do so, companies should understand their customers’ interests and act accordingly. One popular method for this purpose is building recommendation engines to make personalized suggestions. In this project, collaborative filtering methods with implicit feedback are used to make recommendations to users of theSteam platform. The recommendation systems are built using two different matrix factorization techniques, Alternating Least Squares and Bayesian Personalized Ranking. Different models are created with implicit playtime data of the users and the results are evaluated by using Precision at k metric. Additionally, similar items that are offered by the models are analyzed. Results show that the models are considerably successful at finding personal choices and similar items. The best model finds the item in the libraries of 33% ofthe users.Master Term Project Prediction of Credit Card Default(MEF Üniversitesi Fen Bilimleri Enstitüsü, 2021) Akalın, Selçuk; Utku KoçAs profitable customer acquisition becomes more and more critical for the banking sector in terms of competition, the requirement to predict customer defaults with different machine learning algorithms is increasing. Thanks to similar practices, possible damages can be prevented. Due to the rapid change of machine learning with the changing technology, the fields of application and development in different sectors are also changing and developing rapidly. In this study, the aim is to make a comparison over model outcomes and making observations on outcomes to determine the areas that can be developed or researched with running different supervised and unsupervised machine learning algorithms on the final dataset gathered by doing following methods such as key points discovered in exploratory data analysis on an imbalanced credit card dataset, generating different features according to learned key points, eliminating imbalance with different oversampling and undersampling methods.Master Term Project Credit Card Froud Detection Using Machine Learning(MEF Üniversitesi Fen Bilimleri Enstitüsü, 2021) Erdoğan, Tibet; Duygu Taş KütenThis project aims to find the most efficient machine learning models to detect fraudulent transactions on credit cards. The dataset used for this project consists of credit card transactions made by European cardholders in September 2013. This dataset presents transactions that have occurred in two days, where there are 492 frauds out of 284,807 transactions. Machine learning methods, such as decision trees, logistic regression and random forest classifier are used to predict the fraudulent transactions. Performance of these machine learning models are compared to achieve the highest accuracy. According to the results, it is found that the random forest classifier is the most effective model, and the SMOTE technique used to overcome the data imbalance performs better than the under-sampling technique. It is also observed that the models employed with the under-sampled data misclassify large number of non-fraud transactions as fraud. Lastly, by means of the random forest with the over-sampling technique (SMOTE), it is observed that the feature “V13” has the most important role in detecting fraud.Master Term Project Ad Click Prediction Using Machine Learning Algorithms(MEF Üniversitesi Fen Bilimleri Enstitüsü, 2021) Uncu, Nazlı Tuğçe; Hande KüçükaydınOnline advertising has a great potential to boost business’ revenue. One of the key metrics that defines the success of online ad campaigns is click through rate (CTR) which indicates the total number of clicks received in relation to the total impression. Therefore, the click prediction systems, which have the aim of increasing the click through rates of online advertising campaigns by predicting the clicks, have become essential for businesses. For this reason, predicting whether an advertisement will receive a click fromthe user or not attracts the attention of researchers from the both industry and academia. In this capstone project, the click prediction is studied by using Avazu’s click logs dataset. The effects of having high cardinality categorical features and imbalanced data are examined during data preprocessing phase and then relevant features are selected to be used in modeling. The methods that are used for this classification problem are decision trees, random forest, k-nearest neighbor, extreme gradient boosting, and logistic regression. According to the results of the study, extreme gradient boosting shows the best performance.Master Term Project QPICAR Deep Learning(MEF Üniversitesi Fen Bilimleri Enstitüsü, 2021) Beğde, Özge; Tuna ÇakarThe aim of the project is to train a smart tool kit named "Sunfounder Raspberry Pi Robot Car" to move without hitting the walls in a closed area. The goal is to maximize the driving time without crashing by reducing the number of hits. Ultrasonic sensor data collected from the vehicle are processed with reinforcement learning and deep reinforcement learning algorithms and the results are compared. In this study, Python programminglanguage is used. In this study, firstly, the Q-Learning method, which is a reinforcement learning algorithm based on Markov decision processes, is used. The method basically relies on a memory table, Q-Table, in which the Q-values of the agent moving from one state to another are kept. This table is updated according to the results of the Bellman equation in every action of the agent, and as a result of this iterative process, it is optimized to provide that the agent moves to maximize its rewards. Deep Q-Learning (DQN) is used as a deep reinforcement learning algorithm. This algorithm was developed by the DeepMind Technologies team in 2013. Basically, it is based on the use of the Bellman equation, which is an element of the Q-Learning method, incombination with neural networks. This method is often used for training agents in complex and multidimensional environments such as video games. Due to the different type of the data used on the algorithm, minor changes were made to adapt it to the study. RElu and Softplus are used as activation functions. The results of the training process show that the DQN algorithm has an important advantage in terms of training the agent in a short time. At this point, the results are in accordance with other academic studies demonstrating the success of the DQN algorithm for complex environments.For future work, by differentiating the equipment that collects data on the vehicle, different data types such as image, temperature value, oxygen value can be collected and processed. At the same time, with changes to the reward setup in the algorithm, the agent can be trained to move to a specific target or to take actions to avoid a specific target.Master Term Project Price Prediction Using Machine Learning Techniques: an Application To Vacation Rental Properties(MEF Üniversitesi Fen Bilimleri Enstitüsü, 2021) Ay, Oğuz; Hande KüçükaydınPricing is a subjective process that highly depends on person. There is no general rule to price a house. That is why there is both overpriced and underpriced rental houses in rental listings in websites such as AirBnB. In order to reduce the effect of subjective pricing, a general machine learning model is built in this project to make more objective price predictions.In the literature, there are different machine learning models to make numeric predictions. Physical features of houses are used as an input to make inferences about the price of a house. These machine learning models can identify the relations between features and the price and make the predictions with respect to features of a new listing house that has not been priced before.In this project, six different machine learning models are developed. These are linear regression, ridge regression, support vector regressor, random forest regressor, light gradient boosting machine regressor and extreme gradient boosting regressor. The performances of all models are compared, and the best model is selected for hyper-parameter tuning to make more accurate predictions.Master Term Project Forecasting Organic Traffic With Different Source of Data(MEF Üniversitesi Fen Bilimleri Enstitüsü, 2021) Çolak, Mehtap; Özgür ÖzlükIn this project, the results are compared using different data sets for the organic traffic forecasting of a website. Two different models were developed based on the data obtained from Google Search Console (GSC), Google Analytics (GA), Ahrefs and Google Trends and trained with XGBoost and Random Forest machine learning algorithms. Although the .. value and accuracy rate of the first model developed on the GSC, GA and Ahrefs data obtained between 2019-2020 was high; it is not suitable for predictive analysis because the data sets consist of dependent variables. The second model was developed with Google Trends data for brand and non-brand queries with the highest Impression value. The future trends of the relevant queries were predicted using the Prophet algorithm. Through this model, Impression values of the relevant website were estimated for the remainder of 2021.Master Term Project Customer Segmentation and Customer Churn Prediction for Babil.com(MEF Üniversitesi Fen Bilimleri Enstitüsü, 2021) Çakar, Berk; Evren GüneyIn the past decade, a lot of players have joined into e-commerce market and competition in the market has been increasing lately. The e-commerce companies want to use their resources more efficiently to stay ahead in the competition. Personal communication with customers, increasing customer loyalty, acquiring new customers and preventing customer churn are some of the ways to achieve this goal.Babil.com is an e-retailer that sells books online and it is one of the companies which wants to stay ahead in the competition. It is founded in 2013 and now it is a 8 years old mature company. So, instead of spending much resources on acquiring new customers, trying to keep existing customers and increasing retention rate is a more ideal goal for the company. Also, personal communication with customers and reaching them with the right product in the right time is crucial.In this project, a customer segmentation with two levels is implemented to help Babil.com. For the first level of segmentation, customers’ value to company is identified by RFM segmentation and in the second level of segmentation customers’ behaviors are identified by K-Means clustering. To prevent customer churn, a machine learning algorithm which predicts customers who will churn in the next 6 months. With this algorithm, it will be easy to take an action for the right customers in the right time.Master Term Project Airbnb Host Recommendation Engine(MEF Üniversitesi Fen Bilimleri Enstitüsü, 2021) Arslan, Batuhan; Özgür ÖzlükIn this project, a fifth rule is proposed to reveal guests ' comments about hosts using the recommendation system and sentiment analysis for the super hosts' selection for Airbnb. This project is aimed to contribute to Airbnb's selection of Super hosts. In this study, sentiment analysis and comment data are examined, and polarity scores are created for use in suggestion systems. A collaborative filtering method is used for the recommendation system. The FunkSVD algorithm received the best RMSE score. Polarity scores are estimated for each latent user by looking at the host and listing id. The recommendation system developed ranked the polarity scores of hosts for each user.