Amplify Business Intelligence with Visual Analytics
In the era of big data, the rich data accumulated by the financial industry have brought new inspiration to business intelligence and knowledge services. Processing vast amounts of information into knowledge and improving data utilization capabilities have become opportunities for the development of business intelligence. Visualization has a direct and close connection with knowledge expression and is an important means of interpreting complex data.
We are FinVis group of HKUST VisLab. In order to help people have a deeper understanding of financial data, we have explored this study for years. In order to effectively organize financial data and better serve users to business intelligence, we emphasize visual analytics rather than visualization, aiming to provide a new perspective for the exploration of the financial field. The areas we cover include but are not limited to, cryptocurrency, quantitative trading, financial news, etc.
Financial areas data, quantitative trading, stock, funds, insurance, cryptocurrency, etc. are all our playgrouds to provide business intelligence via visual analytics.
Advanced data mining, deep learning models guarantee us to tackle with billions of transaction logs, demographic data or text extracted from financial reports and social media.
Except the basic visualization representation, we introduce and amplify visual anlytics to facilitate business intelligence.
Would you like to know more or just discuss something?
Our research covers below topics. We're very excited about the future of our team.
This work has been accpeted by IEEE Transactions on Visualization and Computer Graphics 2018.
The emerging prosperity of cryptocurrencies, such as Bitcoin, has come into the spotlight during the past few years. Cryptocurrency exchanges, which act as the gateway to this world, now play a dominant role in the circulation of Bitcoin. Thus, delving into the analysis of the transaction patterns of exchanges can shed light on the evolution and trends in the Bitcoin market, and participants can gain hints for identifying credible exchanges as well. Not only Bitcoin practitioners but also researchers in the ﬁnancial domains are interested in the business intelligence behind the curtain. However, the task of multiple exchanges exploration and comparisons has been limited owing to the lack of efﬁcient tools. Previous methods of visualizing Bitcoin data have mainly concentrated on tracking suspicious transaction logs, but it is cumbersome to analyze exchanges and their relationships with existing tools and methods. In this paper, we present BitExTract, an interactive visual analytics system, which, to the best of our knowledge, is the ﬁrst attempt to explore the evolutionary transaction patterns of Bitcoin exchanges from two perspectives, namely, exchange versus exchange and exchange versus client. In particular, BitExTract summarizes the evolution of the Bitcoin market by observing the transactions between exchanges over time via a massive sequence view. A node-link diagram with ego-centered views depicts the trading network of exchanges and their temporal transaction distribution. Moreover, BitExTract embeds multiple parallel bars on a timeline to examine and compare the evolution patterns of transactions between different exchanges. Three case studies with novel insights demonstrate the effectiveness and usability of our system.
Market participants and businesses continually spare no eﬀorts towards making a smarter decision during the past decades. From the perspective of data statistics and data analysis, the progress that based on the enormous ﬁnancial data has drawn a lot of attention not only in the industry but also the academic. However, owing to the high diversity, large volume, and unstructured characteristic, the visual analysis has great potential among data exploration progress. The tasks summarized by ﬁnancial practitioners provide a more clear direction for computer science ﬁelds. However, there are limited visual analysis systems developed to solve those tasks eﬃciently. Proper summarization combining main functions and applications in ﬁnancial areas should be emphasized to get an overview of state-of-art work and future potential research ﬁelds.
In this survey, we ﬁrst introduce the background and motivation of visual analysis on ﬁnancial data and give a comprehensive review of typical tasks like anomaly detection, predictive analysis, correlative analysis, and application in FinTech. Finally, we conclude the survey with a discussion of future research directions.
This work has been accepted by 2016 International Conference on Big Data and Smart Computing (BigComp).
When reading ﬁnancial news, although there are critics explaining the ﬂuctuation of Economic indexes in articles everyday, the news often assert bias on authors’ favorite opinions. On the other hand, the amount of ﬁnancial news published these days is staggering with diversiﬁed opinions on the same issues. Unless with acumen for the whole environment, audience will ﬁnd hard to stay objective and identify useful information from the mass media. If computer is granted ability to analyze all news and generate a narrative that addresses all concerns related to the news, all kinds of readers can obtain a more compelling story. Nowadays, Narrative Visualization is a popular technique for news media to deliver reader driven stories, and a potential ﬁeld for application side. In this paper, we ﬁrst identify ﬁnancial news with two features: polarity associated with each news and, factors impacting the indexes or being impacted by the indexes. Then we apply these features to explain the price ﬂuctuation and explain the Socio-economic relationships between price and different topics. Finally, two case studies are conducted to demonstrate the effectiveness and usefulness of FinaVistory in helping users with different purposes to understand the stories behind Europe unemployment after 2008 ﬁnancial crisis and oil price in 2014.
This work has been accepted by 2014 International Conference on Big Data and Smart Computing (BigComp).
Although many current visualization approaches to time-series data can show a good general trend of a topic or theme over time, most cannot help people gain a deeper understanding of key issues. They may illustrate how some key issues come up and disappear from time to time, but they typically provide limited information about relationships of interest. Financial and economic analysts are often interested in how financial or economic performance indicators interplay or change over time. With a set of well-defined and commonly used equations or indicators in the domain of Economics and Finance, we can refine our visualization by keeping track of these variables. In this paper, we make use of a line plot layout to track some of these indicators and leverage word clouds to reveal how these indicators are affected by the changes in social and economic environments.