From finance to ITS: traffic data fusion based on Markowitz' portfolio theory

Abstract

SUMMARYTraffic data fusion has much to do with combining available or considered data sources in the best possible way. In this, it is very similar to optimizing a portfolio of financial assets in regard of return and risk. This article draws the analogy between these two mostly different scientific worlds, i.e. finance and engineering. Similarities and differences in context of weighted-mean data fusion based on numerical traffic flow measurements such as travel times or speeds are discussed. This, in particular, includes guessing the potential benefit of negative weights. Optimal weights are derived following a strict mathematical theory based on assumptions (parameters) about systematic bias and correlations of the considered data sources. Moreover, a specific way of reducing the systematic bias of the fusion results is proposed and compared to common methods. The whole approach is demonstrated based on position data from two independent vehicle fleets in Athens, Greece. In this context, the problem of parameter calibration is solved by applying an advanced tool for such floating car data systems, called "self-evaluation". The experiments show that the proposed methods reliably reduce the systematic bias and variance of the fusion results with regard to the original data as well as in comparison to the naïve fusion approach that uses equal weights for all data sources.

Fusion based estimation of the a-priori probability distribution of unknown non-stationary processes

“…Further, it is quite interesting that specifically improvements are made in case homogeneous sensors (or sensors that provide similar accuracies) are used. Although, usually each additional sensor (in case of an unbiased sensor it almost does not matter how good it is [15]) contributes by improving the fused data in the stationary case; however, in terms of adaptive, non-stationary data fusion it does matter, which types and accuracies of sensors are combined.…”

“…In case of experiment 3 stationary data fusion is superior to adaptive fusion independently of the sensors applied. • Although it is expected that any additional sensor improves the accuracy and reliability of the resulting data (see [15] in case of unbiased sensors), it is not the case for adaptive fusion. The combination of an accurate sensor (e.g.…”

Industry Asset Allocation Portfolio Analysis

“…[5] And Neumann says the problem of parameter calibration is solved by applying an advanced tool for such floating car data systems, called "selfevaluation". [6] The research of this article focuses on the application side, through the flexible use of a variety of theories to provide the industry with an excellent portfolio of risky assets. It flexibly combines Markowitz theory with real stocks to achieve a breakthrough leap.…”

Special issue: Smart transportation: Theory and practice

“…Neumann et al [7] addressed the traffic data fusion problem of using multiple data sources to make better estimation of travel times instead of using a single data source. Based on Markowitz' portfolio theory in finance, they proposed an optimized weighted-mean approach to determine the optimal fusion of multiple data sources.…”