During my stay as a visiting student at the HCIL laboratory at the University of Maryland, I was given the task of devising a new user interface for a time-series forecasting tool, TimeSearcher. The tool was aimed at economists who were interested at forecasting how a particular time-series would evolve in the future given a dataset of similar ones (for example, the final price of an online auction given a dataset of ended auction of similar items). Numerous parameters influenced the outcome of the forecast but the previous interface was very difficult to use because it did not allow users to visually compare the changes different values would cause.


I designed a new interface that offered multiple visualizations of the outcome of the forecast. For each parameters, users could choose a sample value and the interface would display how the forecast would look like at that value and at neighbouring ones. In this way, for each parameter, users wera able to visually compare several time-series forecasts at the same time. This work went on to become my Masters’ Thesis in Computer Science and resulted in a successful publication at InfoVis 2007.


↑ Jump to Top

P. Buono, C. Plaisant, A.L. Simeone, A. Aris, B. Shneiderman, G. Shmueli, and W. Jank.
Similarity-Based Forecasting with Simultaneous Previews: a River Plot Interface for Time Series Forecasting
In Proceedings of Information Visualization 2007 (IV 2007). IEEE, pp. 191-196.

PDF Version of Document

P. Buono, and A.L. Simeone.
Interactive Shape Specification for Pattern Search in Time Series
Demo at Advanced Visual Interfaces, 2008 (AVI 2008). ACM, pp. 480-481.

PDF Version of Document

Time-series forecasting has a large number of applications. Users with a partial time series for auctions, new stock offerings, or industrial processes desire estimates of the future behavior. We present a data driven forecasting method and interface called similarity-based forecasting (SBF). A pattern matching search in an historical time series dataset produces a subset of curves similar to the partial time series. The forecast is displayed graphically as a river plot showing statistical information about the SBF subset. A forecasting preview interface allows users to interactively explore alternative pattern matching parameters and see multiple forecasts simultaneously. User testing with 8 users demonstrated advantages and led to improvements.
author={Buono, P. and Plaisant, C. and Simeone, A. and Aris, A. and Shneiderman, B. and Shmueli, G. and Jank, W.},
booktitle={Information Visualization, 2007. IV '07. 11th International Conference},
title={Similarity-Based Forecasting with Simultaneous Previews: A River Plot Interface for Time Series Forecasting},
keywords={data visualisation;graphical user interfaces;time series;data driven forecasting method;forecasting preview interface;historical time series dataset;new stock offerings;partial time series;pattern matching search;river plot interface;similarity-based forecasting;time series forecasting;Data visualization;Economic forecasting;Laboratories;Pattern matching;Predictive models;Rivers;Smoothing methods;Technological innovation;Testing;Weather forecasting},
Time series analysis is a process whose goal is to understand phenomena. The analysis often involves the search for a specific pattern. Finding patterns is one of the fundamental steps for time series observation or forecasting. The way in which users are able to specify a pattern to use for querying the time series database is still a challenge. We hereby propose an enhancement of the SearchBox, a widget used in TimeSearcher, a well known tool developed at the University of Maryland that allows users to find patterns similar to the one of interest.
author = {Buono, Paolo and Simeone, Adalberto Lafcadio},
title = {Interactive Shape Specification for Pattern Search in Time Series},
booktitle = {Proceedings of the Working Conference on Advanced Visual Interfaces},
series = {AVI '08},
year = {2008},
isbn = {978-1-60558-141-5},
location = {Napoli, Italy},
pages = {480--481},
numpages = {2},
url = {http://doi.acm.org/10.1145/1385569.1385666},
doi = {10.1145/1385569.1385666},
acmid = {1385666},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {information visualization, interactive system, interactive visualization, visual querying},