Interactive Probing of Multivariate Time Series Prediction Models: A Case of Freight Rate Analysis

TL;DR

This paper introduces an interactive tool for probing and analyzing multivariate time series models, specifically applied to freight rate prediction, enabling sensitivity analysis and scenario exploration for industry practitioners.

Contribution

The paper presents a novel interactive probing tool that allows users to create, modify, and analyze what-if scenarios for multivariate time series models in freight analysis.

Findings

Tool enables intuitive scenario creation and analysis.

Practitioners successfully used the tool for freight index projections.

Case study demonstrates practical utility in industry settings.

Abstract

We present an interactive probing tool to create, modify and analyze what-if scenarios for multivariate time series models. The solution is applied to freight trading, where analysts can carry out sensitivity analysis on freight rates by changing demand and supply-related econometric variables and observing their resultant effects on freight indexes. We utilize various visualization techniques to enable intuitive scenario creation, alteration, and comprehension of time series inputs and model predictions. Our tool proved to be useful to the industry practitioners, demonstrated by a case study where freight traders are given hypothetical market scenarios and successfully generated quantitative freight index projection with confidence.