Browsing by Subject "Data analytics"

Now showing 1 - 8 of 8

Open Access
ALACA: a platform for dynamic alarm collection and alert notification in network management systems
(John Wiley and Sons Ltd., 2017) Solmaz, S. E.; Gedik, B.; Ferhatosmanoğlu, H.; Sözüer, S.; Zeydan, E.; Etemoğlu, Ç. Ö.
Mobile network operators run Operations Support Systems that produce vast amounts of alarm events. These events can have different significance levels and domains and also can trigger other ones. Network operators face the challenge to identify the significance and root causes of these system problems in real time and to keep the number of remedial actions at an optimal level, so that customer satisfaction rates can be guaranteed at a reasonable cost. In this paper, we propose a scalable streaming alarm management system, referred to as Alarm Collector and Analyzer, that includes complex event processing and root cause analysis. We describe a rule mining and root cause analysis solution for alarm event correlation and analyses. The solution includes a dynamic index for matching active alarms, an algorithm for generating candidate alarm rules, a sliding window–based approach to save system resources, and a graph-based solution to identify root causes. Alarm Collector and Analyzer is used in the network operation center of a major mobile telecom provider. It helps operators to enhance the design of their alarm management systems by allowing continuous analysis of data and event streams and predict network behavior with respect to potential failures by using the results of root cause analysis. We present experimental results that provide insights on performance of real-time alarm data analytics systems. Copyright © 2017 John Wiley & Sons, Ltd.
Open Access
Big data analytics, order imbalance and the predictability of stock returns
(Elsevier, 2021-09-24) Akyildirim, E.; Şensoy, Ahmet; Gulay, G.; Corbet, S.; Salari, Hajar Novin
Financial institutions have adopted big data to a considerable extent to provide better investment decisions. Consequently, high-frequency algorithmic traders use a vast amount of historical data with various statistical models to maximize their trading profits. Until recently, high-frequency algorithmic trading was the domain of institutional traders with access to supercomputers. Nowadays, any investor can potentially make high-frequency trades because of easy access to big data and software to analyze and execute trades. With that in mind, Borsa Istanbul introduced real time big data analytics as a product to its customers. These analytics are derived in real time from order book and trade data and aim to level the playing field between investment firms and retail traders. Using classical benchmark models in the literature, we show that Borsa Istanbul’s order imbalance-based data analytics are useful in predicting both time-series and cross-sectional intraday excess future returns, proving that this product is extremely beneficial to market participants, particularly day traders.
Open Access
Data analytics in stock markets
(2019-06) Salari, Hajar Novin
One of the important strategies that is employed in finance is data analytics. Data Analytics is the science of investigating raw data with intention of drawing meaningful information and useful conclusions. Recently, organizations started to consider data analytics as a way to improve business processes and, use the collected information in operational efficiencies for achieving revenue growth. In recent years, the usage of data analytics is rapidly growing for many other reasons, such as, optimizing business processes, increasing revenue, and improving customer interactions. In this research two kinds of data analytics, order imbalances and order flow imbalances are studied and two groups of models extended according them. These regression models are based on level regressions and percentage changes, and trying to answer whether data analytics can forecast one minute a head of price return for each stock or not. Moreover, the results are analyzed and interpreted for 27 stocks of Borsa Istanbul. In the next step, for understanding the power of prediction of data analytics, Fama-Macbeth regression is considered. In the first step, each portfolio’s return is regressed against one or more factor of time series. In the second step, the cross-section of portfolio returns is regressed against the factors, at each time step. Then, we discuss the Long-Short Portfolio approach which is widely used in finance literature. This method is an investing strategy that takes long positions in stocks that are expected to ascend and short positions in stocks that are expected to descend. In this part we show the number of days that are positive or negative and provide the t stats that adjusted by NW procedure for all data analytics in each day for this method. Finally, we discuss about the market efficiency and show whether according to our analysis Borsa Istanbul is an efficient market or not.
Open Access
Efficient community identification and maintenance at multiple resolutions on distributed datastores
(Elsevier BV, 2015) Aksu, H.; Canim, M.; Chang, Yuan-Chi; Korpeoglu, I.; Ulusoy, Özgür
The topic of network community identification at multiple resolutions is of great interest in practice to learn high cohesive subnetworks about different subjects in a network. For instance, one might examine the interconnections among web pages, blogs and social content to identify pockets of influencers on subjects like 'Big Data', 'smart phone' or 'global warming'. With dynamic changes to its graph representation and content, the incremental maintenance of a community poses significant challenges in computation. Moreover, the intensity of community engagement can be distinguished at multiple levels, resulting in a multi-resolution community representation that has to be maintained over time. In this paper, we first formalize this problem using the k-core metric projected at multiple k-values, so that multiple community resolutions are represented with multiple k-core graphs. Recognizing that large graphs and their even larger attributed content cannot be stored and managed by a single server, we then propose distributed algorithms to construct and maintain a multi-k-core graph, implemented on the scalable Big Data platform Apache HBase. Our experimental evaluation results demonstrate orders of magnitude speedup by maintaining multi-k-core incrementally over complete reconstruction. Our algorithms thus enable practitioners to create and maintain communities at multiple resolutions on multiple subjects in rich network content simultaneously.
Open Access
Forecasting high-frequency excess stock returns via data analytics and machine learning
(Wiley-Blackwell Publishing Ltd., 2021-11-23) Akyıldırım, E.; Nguyen, D. K.; Şensoy, Ahmet; Šikić, M.
Borsa Istanbul introduced data analytics to present additional information about its market conditions. We examine whether this product can be utilized via various machine learning methods to predict intraday excess returns. Accordingly, these analytics provide significant prediction ratios above 50% with ideal profit ratios that can reach up to 33%. Among all the methods considered, XGBoost (logistic regression) performs better in predicting excess returns in the long-term analysis (short-term analysis). Results provide evidence for the benefits of both the analytics and the machine learning methods and raise further discussion on the semistrong market efficiency.
Open Access
Forecasting high‐frequency excess stock returns via data analytics and machine learning
(John Wiley and Sons Inc., 2023-01) Akyildirim, E.; Nguyen, D.K.; Şensoy, Ahmet; Šikić, M.
Borsa Istanbul introduced data analytics to present additional information about its market conditions. We examine whether this product can be utilized via var ious machine learning methods to predict intraday excess returns. Accordingly, these analytics provide significant prediction ratios above 50% with ideal profit ratios that can reach up to 33%. Among all the methods considered, XGBoost (logistic regression) performs better in predicting excess returns in the long‐term analysis (short‐term analysis). Results provide evidence for the benefits of both the analytics and the machine learning methods and raise further discussion on the semistrong market efficiency.
Open Access
Graph aware caching policy for distributed graph stores
(IEEE, 2015-03) Aksu, Hidayet; Canım, M.; Chang, Y.-C.; Körpeoğlu, İbrahim; Ulusoy, Özgür
Graph stores are becoming increasingly popular among NOSQL applications seeking flexibility and heterogeneity in managing linked data. Conceptually and in practice, applications ranging from social networks, knowledge representations to Internet of things benefit from graph data stores built on a combination of relational and non-relational technologies aimed at desired performance characteristics. The most common data access pattern in querying graph stores is to traverse from a node to its neighboring nodes. This paper studies the impact of such traversal pattern to common data caching policies in a partitioned data environment where a big graph is distributed across servers in a cluster. We propose and evaluate a new graph aware caching policy designed to keep and evict nodes, edges and their metadata optimized for query traversal pattern. The algorithm distinguishes the topology of the graph as well as the latency of access to the graph nodes and neighbors. We implemented graph aware caching on a distributed data store Apache HBase in the Hadoop family. Performance evaluations showed up to 15x speedup on the benchmark datasets preferring our new graph aware policy over non-aware policies. We also show how to improve the performance of existing caching algorithms for distributed graphs by exploiting the topology information. © 2015 IEEE.
Open Access
Towards interactive data exploration
(Springer, 2019) Binnig, C.; Basık, Fuat; Buratti, B.; Çetintemel, U.; Chung, Y.; Crotty, A.; Cousins, C.; Ebert, D.; Eichmann, P.; Galakatos, A.; Hattasch, B.; Ilkhechi, A.; Kraska, T.; Shang, Z.; Tromba, I.; Usta, Arif; Utama, P.; Upfal, E.; Wang, L.; Weir, N.; Zeleznik, R.; Zgraggen, E.; Castellanos, M.; Chrysanthis, P.; Pelechrinis, K.
Enabling interactive visualization over new datasets at “human speed” is key to democratizing data science and maximizing human productivity. In this work, we first argue why existing analytics infrastructures do not support interactive data exploration and outline the challenges and opportunities of building a system specifically designed for interactive data exploration. Furthermore, we present the results of building IDEA, a new type of system for interactive data exploration that is specifically designed to integrate seamlessly with existing data management landscapes and allow users to explore their data instantly without expensive data preparation costs. Finally, we discuss other important considerations for interactive data exploration systems including benchmarking, natural language interfaces, as well as interactive machine learning.