Completed

Machine Learning methods have long been applied to financial data. We explore the correlation (or the lack thereof) of financial data, such as the BIST 100 index or individual stock prices, to features extracted from financial news and past data. We intend to use the advancements in text classification and Natural Language Processing capabilities in general, and machine learning models to extract the features of Turkish news documents and stock price series using statistical methods and to analyze the correlation of the extracted features with the financial data.

Beta lactamase antibiotics are one of the widely used antibiotics in the world. They constitute most of the worldwide antibiotic usage and used for bacterial infections. Antibiotic resistance of bacterial organisms is an important health issue if we think about today’s world. Our aim is to check all the information about beta lactamase on the internet and journals, and retrieve all data to create our database system which you can easily search proteins, inhibitors and ligands that are related to beta lactamase enzymes.

Player rating systems are essential nearly to any game situated in different contexts (video games, sports etc). This need arises from the fact that an unbalanced match is not enjoyable to any of it’s competitors. In this project we assume a generative model responsible for creation of past match results and we attempt to infer approximate posterior skills distributions by using three different algorithms: Metropolis-Hastings, Gibbs Sampler and Expectation Propagation.

In this project, we present several algorithms that infers a Bayesian network that explains the observed data naturally (maximizing p(Model | Data)) by using Stochastic Gradient Langevin Dynamics MCMC, thermodynamic integration and generalized importance sampling. Here, we assumed that Bayesian network has a fixed graph topology and unobserved random variables (interestingly this assumption makes the model more general).

The motivation behind this project is to be able to make a sentiment analysis on Turkish financial documents. Classify-ing financial news as negative or positive helps predicting the change in stock price for a particular company. In our work, we process more than 20,000 documents obtained from financial institutions in Turkey. We translate Loughran & McDonald's word list into Turkish and label the news based on the number of negative words they contain. We then construct a Logistic Regression model with Ll penalization using bag-of-words ap-proach to predict the labels of news.