Optimization

The field of natural language processing (NLP) has evolved significantly in recent years. In this chapter we consider two leading and well-established methodologies, namely, those due to Loughran McDonald, and FinBERT. We then contrast our approach to these two approaches and compare our performance against these methods which are considered to be benchmarks. We use S&P 500 market data for our investigations and describe the results obtained following our strategies. Our main consideration is the Earnings Calls for the S&P 500 stocks. We vindicate our findings and present the performance of our trading and fund management strategy which shows better results.

Keywords— Natural Language Processing, Sentiment Analysis, Earnings Calls

Convex quadratic programming as applied to portfolio planning is established and well understood. In this paper, presented in two parts, we highlight the importance of choosing an algorithm that processes a family of problems efficiently. In Part I (published in issue 8/3), in particular, we described an adaptation of the simplex method for Quadratic Programming (QP). The method not only takes advantage of the sparse features of simplex, the use of the duality property makes it ideally suited for processing the discrete optimization models. Part II of the paper considers a family of discrete QP formulations of the portfolio problem, which capture threshold constraints and cardinality restrictions. We describe the adaptation a novel method branch, fix and relax to process this class of models efficiently. Theory and computational results are presented.

We consider a strategic supply chain planning problem formulated as a two-stage stochastic integer programming (SIP) model. The strategic decisions include site locations, choices of production, packing and distribution lines, and the capacity increment or decrement policies. The SIP model provides a practical representation of real-world discrete resource allocation problems in the presence of future uncertainties which arise due to changes in the business and economic environment. Such models that consider the future scenarios (along with their respective probabilities) not only identify optimal plans for each scenario, but also determine a hedged strategy for all the scenarios. We (1) exploit the natural decomposable structure of the SIP problem through Benders decomposition, (2) approximate the probability distribution of the random variables using the generalized lambda distribution, and (3) through simulations, calculate the performance statistics and the risk measures for the two models, namely the expected-value and the here-and-now.

The introduction of new technologies and concepts has redefined the relative positioning of information systems (IS) and decision technologies in a corporate context. Corporate IS have been extended to include not only transaction processing databases but also analytical databases, often known as Data Warehouses. On-line analytical processing (OLAP) , as introduced by Codd et al. , is capable of capturing the structure of the real world data in the form of multidimensional tables which are known as ‘datacubes’ by management information systems (MIS) and statistical systems specialists. Manipulation and presentation of such information through multidimensional views and graphical displays provide invaluable support for the decision-maker. We illustrate the natural coupling, which exists between data modelling, symbolic modelling and ‘What if’ analysis phases of a decision support system (DSS) . In particular, we explore the power of roll-up and drill-down features of OLAP and show how these translate into aggregation and disagreggation of the underlying decision models. Our approach sets out a paradigm for analysing the data, applying DSS tools and progressing through the information value chain to create organisational knowledge.

LP models are usually constructed using index sets and data tables which are closely related to the attributes and relations of relational database (RDB) systems. We extend the syntax of MPL, an existing LP modelling language, in order to connect it to a given RDB system. This approach reuses existing modelling and database software, provides a rich modelling environment and achieves model and data independence. This integrated software enables Mathematical Programming to be widely used as a decision support tool by unlocking the data residing in corporate databases.

We report a computational study of two-stage SP models on a large set of benchmark problems and consider the following methods: (i) Solution of the deterministic equivalent problem by the simplex method and an interior point method, (ii) Benders decomposition (L-shaped method with aggregated cuts), (iii) Regularised decomposition of Ruszczy4nski (Math Program 35:309-333, 1986), (iv) Benders decomposition with regularization of the expected recourse by the level method (Lemarichal et al. in Math Program 69:111-147, 1995), (v) Trust region (regularisation) method of Linderoth and Wright (Comput Optim Appl 24:207-250, 2003). In this study the three regularisation methods have been introduced within the computational structure of Benders decomposition. Thus second-stage infeasibility is controlled in the traditional manner, by imposing feasibility cuts. This approach allows extensions of the regularisation to feasibility issues, as in Fabian and Szuke (Comput Manag Sci 4:313-353, 2007). We report computational results for a wide range of benchmark problems from the POSTS and SLPTESTSET collections and a collection of difficult test problems compiled by us. Finally the scale-up properties and the performance profiles of the methods are presented.

Convex quadratic programming (QP) as applied to portfolio planning is established and well understood. In this paper, presented in two parts, we highlight the importance of choosing an algorithm that processes a family of problems efficiently. In Part I in particular we describe an adaptation of the simplex method for QP. The method takes advantage of the sparse features of simplex and the use of the duality property makes it ideally suited for processing the discrete optimization models. Part II (to be published in issue 8/4) of the paper considers a family of discrete QP formulations of the portfolio problem, which captures threshold constraints and cardinality restrictions. We describe the adaptation of a novel method branch, fix and relax to process this class of models efficiently. Theory and computational results are presented.

Today’s marketplace is becoming increasingly dynamic and volatile. As consumers become more sophisticated, they demand the right product at the right time, at the right price, and at the right place. Whereas quality was the competitive weapon of the 80s, customer responsiveness, or time-to-market is the differentiator today. In many industries, hyper-competition is forcing many enterprises to fundamentally change the way business is conducted in order to service. Given these challenges, traditional paradigms for business management are ineffective. At the same time, businesses face tremendous pressure from their stakeholders to increase ROA, profit contribution and customer responsiveness. Given the complexity of a typical supply chain, supply chain planning systems (also known Given the complexity of a typical supply chain, supply chain planning systems (also known as Advanced Planning Systems) enable companies to intelligently manage the activities of the supply chain. Every company must perform five basic activities or processes within a supply chain: buy, make, move, store and sell. Within each of these processes, there are short-term decisions (which product should be put on the truck?) and long-term decisions (do we need a new factory to meet demand?). Through the intelligent application of constraint-based principles, we can reduce system inertia by reducing capacity on non-constrained resources without a corresponding increase in system nervousness or instability. Multi-enterprise planning capabilities of an intelligent system should include support for the various command and control structures as well as organizational aspects of the supply chain. The ability to model multiple authority domains and support autonomy with interdependence among the various business functions within a supply chain can provide a great deal of flexibility in managing system inertia. Ideally, the distributed architecture of a decision support system should provide global visibility to the various business units or functions to make decisions that meet both local business objectives as well as the global objective of the entire supply chain. In this white paper we discuss the optimal allocation and utilisation of resources using mathematical optimization techniques. We explain in non-technical terms the success and growing importance of optimization techniques in efficiently processing complex supply chain problems in a cross-section of industry. We highlight the differences between strategic and tactical supply chain models. We set out the sequence of actions, the necessary system issues, the decision making issues and managerial aspects in Supply chain. Through this paper the reader will: 1. appreciate the significance of using optimization techniques in making decisions on industrial problems, 2. be aware of real-life case-studies highlighting the benefits of supply-chain optimization, 3. have access to the relevant and the most recent articles and books on supply chain.

UIMP is a matrix-generator report-writer system designed to aid the realization (generation) of mathematical programming models and also the analysis-reporting of the solutions of such models. The data structure facility of the system allows the underlying structure of a user model to be captured and helps to define such models. This data-structure feature is not only a powerful modelling aid, it also finds use in the analysis of solutions and report generation. The experience of using the system, its shortcomings and possible extensions are also discussed.