Research activities

Intrusion Detection

The unbreakable bond that exists today between devices and network connections makes the security of the latter a crucial element for our society. For this reason, in recent decades we have witnessed an exponential growth in research efforts aimed at identifying increasingly efficient techniques able to tackle this type of problem, such as the Intrusion Detection System (IDS). If on the one hand an IDS plays a key role, since it is designed to classify the network events as normal or intrusion, on the other hand it has to face several well-known problems that reduce its effectiveness. The most important of them is the high number of false positives related to its inability to detect event patterns not occurred in the past (i.e. zero-day attacks).

Anomaly Detection

Anomalies can be defined as patterns or data points that do not conform to a well-defined notion of normal behaviour. In contrast to noise removal and noise accommodation, where noise/anomalies areviewed as a hindrance to data analysis, anomaly detection enables interesting data analysis based on the identification of the anomalies. Data analysis to identfy attacks/anomalies is a crucial task in anomaly detection and network anomaly detection itself is an important issue in network security. Anomaly detection is an important problem that has been researched within diverse research areasand application domains. Many anomaly detection techniques have been specifically developed for certain application domains, while others are more generic.

Graph Embeddings and Link Prediction

Knowledge graphs are being used in the field of machine learning for various applications including question & answering, link prediction, fact checking, entity disambiguation etc. For many of these applications finding the missing relationships in the graph is important to ensure, completeness, correctness and quality. This involves the task of entity prediction and relationship prediction. Basically a knowledge graph is a collection of entities and relationships between them in the form of RDF style triples (h, r, t) where h represents a head entity, t being the tail entity and r the relationship between the head and the tail entity. Entity prediction is, given a h, r of a triple predict t and relationship prediction is, given h, t predict r the type of relationship between them. Graph embedding is an approach that is used to transform nodes, edges, and their features into vector space (a lower dimension) whilst maximally preserving properties like graph structure and information. Graphs are tricky because they can vary in terms of their scale, specificity, and subject. If you turn each node in a graph into an embedding as you would words in sentence, a neural network can learn representations for each node.

Financial Forecasting

A financial forecast is an estimate of future financial outcomes for a company or project, usually applied in budgeting, capital budgeting and / or valuation. Typically, using historical internal accounting and sales data, in addition to external industry data and economic indicators, a financial forecast will be the analyst's modeled prediction of company outcomes in financial terms over a given time period. Arguably, the key aspect of preparing a financial forecast is predicting revenue; future costs, fixed and variable, as well as capital, can then be estimated as a function of sales via "common-sized analysis" - where relationships are derived from historical financial ratios and other accounting relationships. At the same time, the resultant line items must talk to the business' operations:- in general, growth in revenue will require corresponding increases in working capital, fixed assets and associated financing; and in the long term, profitability (and other financial ratios) should tend to the industry average.

Sentiment Analysis

Sentiment analysis (also known as opinion mining or emotion AI) refers to the use of natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information. Sentiment analysis is widely applied to voice of the customer materials such as reviews and survey responses, online and social media, and healthcare materials for applications that range from marketing to customer service to clinical medicine.

Recommender Systems

A recommender system, or a recommendation system, is a subclass of information filtering system that seeks to predict the "rating" or "preference" a user would give to an item. They are primarily used in commercial applications. Recommender systems are utilized in a variety of areas and are most commonly recognized as playlist generators for video and music services like Netflix, YouTube and Spotify, product recommenders for services such as Amazon, or content recommenders for social media platforms such as Facebook and Twitter. These systems can operate using a single input, like music, or multiple inputs within and across platforms like news, books, and search queries. There are also popular recommender systems for specific topics like restaurants and online dating. Recommender systems have also been developed to explore research articles and experts, collaborators, and financial services. 7) Smart Grid Optimization With urging problem of energy and pollution, smart grid is becoming ever important. By gradually changing the actual power grid system, smart grid may evolve into different systems by means of size, elements and strategies, but its fundamental requirements and objectives will not change such as optimizing production, transmission and consumption. Studying the smart grid through modeling and simulation provides us with valuable results which can not be obtained in real world due to time and cost related constraints. However, due to the complexity of the smart grid, achieving optimization is not an easy task, even using computer models. Using approaches in game theory and classification methods the optimization may be achieved with flexibility and scalability.