Global fixed-income returns exhibit highly structured correlations across maturities and economies (data modes), and their modeling therefore requires analysis tools that are capable of directly capturing the inherent multiway couplings present in such multimodal data. Yet, current analyses typically employ “flat-view” multivariate matrix models and their associated linear algebras; these are agnostic to the global data structure and can only describe local linear pairwise relationships between data entries. To address this issue, the authors first show that global fixed-income returns naturally reside on multi-modal lattice data structures, referred to as tensors. This serves as a basis to introduce a multilinear algebraic approach, inherent in tensors, to the modeling of the global term structure underlying multiple interest rate curves. Owing to the enhanced flexibility of multilinear algebra, statistical descriptors, such as correlations, exist between tensor columns and rows (fibers), as opposed to between individual entries in standard matrix analysis. This allows for the expression of the covariance of global returns as a joint multilinear decomposition of the maturity-domain and country-domain covariances. This not only drastically reduces the number of parameters required to fully capture the global return covariance structure, but also makes it possible to devise rigorous and tractable global portfolio management strategies; the authors tailor these specifically to each of the data domains and thereby fully exploit the lattice structure of global fixed-income returns. The ability of the proposed multilinear tensor approach to compactly describe the macroeconomic environment through economically meaningful factors is validated via empirical analysis that demonstrates the existence of maturity-domain and country-domain covariances underlying the interest rate curves of eight developed economies. TOPICS: Fixed income and structured finance, statistical methods, portfolio construction Key Findings ▪ This article shows that global fixed-income returns naturally reside on multimodal lattice data structures, referred to as tensors, which exhibit highly structured correlations across maturities and economies. ▪ The authors introduce a multilinear algebraic approach to the modeling of the global term structure underlying multiple interest rate curves, which allows for the expression of the covariance of global returns as a joint multilinear decomposition of the maturity-domain and country-domain covariances. ▪ This drastically reduces the number of parameters required to fully capture the global return covariance structure and makes it possible to devise rigorous and tractable global portfolio management strategies that are tailored to each of the data domains.

In recent years, the area of financial forecasting has attracted high interest due to the emergence of huge data volumes (big data) and the advent of more powerful modeling techniques such as deep learning. To generate the financial forecasts, systems are developed that combine methods from various scientific fields, such as information retrieval, natural language processing and deep learning. In this paper, we present ASPENDYS, a supportive platform for investors that combines various methods from the aforementioned scientific fields aiming to facilitate the management and the decision making of investment actions through personalized recommendations. To accomplish that, the system takes into account both financial data and textual data from news websites and the social networks Twitter and Stocktwits. The financial data are processed using methods of technical analysis and machine learning, while the textual data are analyzed regarding their reliability and then their sentiments towards an investment. As an outcome, investment signals are generated based on the financial data analysis and the sensing of the general sentiment towards a certain investment and are finally recommended to the investors.

Text mining applications in the investment process involves a complex interaction between computational linguistics, natural language processing (NLP) and the know-how of the financial aspects. Given the progress in big data and multi-modal data fusion, this state-of-the-art survey provides a timely consolidation of this ever evolving topic, together with new perspectives on the acquisition, input, variable relevance, feature extraction, fusion, and decision making based on a conjoint treatment of text and standard financial variables. Such an insight is then used as a basis to introduce an overarching framework for text-based big data in the investment process. The proposed approach is both novel and flexible, making it possible to be seamlessly employed across a variety of investable assets, including stocks, credit instruments, rates, FX and market indices. Another unique aspect is its modularity, whereby both emerging techniques in signal processing and machine learning, as well as traditional econometric techniques, are readily incorporated and combined towards the informed decision. Another virtue of the proposed concept is its ability to identify the semantic nature (context) of the source, even for general text-based sources (financial reports, social media, market news) while at the same time maintaining investors intuition, as news do affect asset prices and market moves. An example of a recent stock market performance during a company takeover process demonstrates the advantages of the proposed framework.