Sabrina: Modeling and Visualization of Financial Data over Time with Incremental Domain Knowledge

Abstract

Figure 1: The different visualizations composing the Sabrina system. The three views (a, b, c) display the firm density and transaction data of an Austrian economy dataset [3]: (a) gradient encoding in blue/red indicates whether the firm density in a hexagonal area increased/decreased in respect to the previous time step; (b) inferred transactions between individual companies; (c) regionally clustered firm data. The interface allows the user to (d) navigate the temporal data dimension, (e) show aggregated details on selected transaction flows, and (f) adjust encoding and filtering options. Tooltips (g) show details on firms within a bin. ABSTRACTInvestment planning requires knowledge of the financial landscape on a large scale, both in terms of geo-spatial and industry sector distribution. There is plenty of data available, but it is scattered across heterogeneous sources (newspapers, open data, etc.), which makes it difficult for financial analysts to understand the big picture. In this paper, we present Sabrina, a financial data analysis and visualization approach that incorporates a pipeline for the generation of firm-to-firm financial transaction networks. The pipeline is capable of fusing the ground truth on individual firms in a region with (incremental) domain knowledge on general macroscopic aspects of the economy. Sabrina unites these heterogeneous data sources within a uniform visual interface that enables the visual analysis process. In a user study with three domain experts, we illustrate the usefulness of Sabrina, which eases their analysis process.

A Review of Geospatial Content in IEEE Visualization Publications

“…Of those papers that constituted a geospatial analysis, the average percentage of geospatial figures per paper was 47.40%. Only two papers had geospatial content in every figure [5] [39]. For papers not classified as geospatial analysis, the average percentage of geospatial figures per paper was only 5.44%.…”

“…Smaller categories were folded into the "Other" class in Fig. 1: two papers using demographic data [25] [38] and one each of the Planetary Science [6], Geoscience [17], Economics [4], Education [16], Text [7], and Art [8] domains.…”

Visual Analytics of Contact Tracing Policy Simulations During an Emergency Response

“…We began this stage by meeting with our collaborators and understanding the data produced by the contact tracing simulation. As our collaborators had no experience working with visualization researchers, we performed rapid prototyping with existing visualization tools that were at our disposal: GMap [GHK10] to demonstrate areas in the data where the infection location was the same, temporal dynamic graph animations of the data drawn in the space‐time cube [SAK20, SAK17,AMA21], time‐to‐colour encodings [BDA∗17] of the data in Jupyter notebooks, and using tools such as Gephi [BHJ09] (see supplementary material for prototypes). These pre‐prototypes provided an initial grounding in the visualization field and allowed us to begin work on visualizations that fit their needs, finding out what worked and what did not work, and most importantly, as mediums to build a healthy dialogue within the team.…”

HFTViz: Visualization for the exploration of high frequency trading data

“…Several previous research papers target the visualization of multidimensional financial data. In Arleo et al 3 the authors use geographical location of companies headquarter office, sector, financial performance (e.g. cash flow, personnel expenses) to create a visualization.…”