Advanced Business Analytics

The decision-making (DM) processes are increasingly playing an important role in business management. The optimization in operational, tactical and strategic decisions can provide to the firm a position of advantage over the competitors. DM is defined as a criteria selection method to choose the best alternative that lets to the firm get the objective. Some of the most important stakeholders involved in the DM processes are described. In this chapter, Decision Trees allow taking into account all the possible alternatives, but it requires a large computational cost, that will be depend of the order of variables. In order to carry out this task as easy as possible, different ranking methods are explained. It is important to say that there is not a method to order the variable providing the best solution in all the cases. This is why several methods are presented such as Top-down-left-right, Depth First Search, The Breath First Search, Level Method and AND Method. Once all the alternatives have been taken into account, Binary Decision Diagrams provide an analytical expression to approach the interrelation between all variables what becomes an optimization function. The optimization function will be usually subject to different constraints related to the availability of resources of the firm. Once the optimization has been carried out, it is easier to establish an optimal strategy to allocate properly the available resources. In this chapter, a case study is presented to facilitate the reader’s understanding of the proposed method hereby. Finally, some conclusions are gathered from the application of this method.

This chapter focuses on the successful collaboration between a research team at the Universidad de La Laguna (Tenerife, Spain) and the firm ITOP Management Consulting, which is a SAP partner mainly interested in developing solutions for SMEs. Company representatives came to our group to propose us both the design of an efficient algorithm to reduce inventory costs in companies, and its eventual integration as an add-on in SAP Business One platform. The problem arises in those firms with storage capacity that should schedule the replenishment orders for several items along a finite planning horizon. After 2 years, the algorithm was finally implemented in C# and .NET. A comprehensive computational experiment was carried out considering a wide range of random instances. The experimental results revealed that heuristic solutions were on average 5 % above the best solution provided by CPLEX optimizer.

The rising wind energy in addition to the increasing number of failures of the larger wind turbines makes necessary the reduction of costs in this industry to make it more competitive in this sector. For this propose the wind energy industry is focused on the reduction of the operation and maintenance (O&M) costs. Condition Monitoring Systems (CMS) are probably the most effective approach to minimize O&M cost and substantially improve the availability, reliability and safety of wind turbines by early detection of the faults. On the other hand, CMS is usual a complex task for any firm because it requires a set of sensors and data acquisition systems to monitor different parameters of the wind turbines. It also requires knowledge and expertise to interpret the large volume of data collected from the wind turbines. In this research work is studied the economic feasibility of a CMS in a wind turbine. The main objective of this work is the development of a life cycle cost (LCC) model for a CMS on wind turbines, being applied to a real case study in Germany. Previously, a review of the literature is realized to describe the state of the art for the economic viability analysis of CMS in wind turbines. This study reveals that the return of the investment depends on the net present value factor, the interest rate of a credit bank and the reduction of failures and energy losses of the wind turbines using CM.

Multi-attribute decision making (MADM) is commonly used when we are comparing more than two courses of actions or alternatives based upon many selected criteria. In this chapter, we present methodologies to conduct MADM analysis. These methodologies include data envelopment analysis (DEA), simple additive weighting (SAW), analytical hierarchy process (AHP), and the technique of order preference by similarity to ideal solution (TOPSIS). We describe each methodology, provide some strengths and limitations of each, discuss tips for sensitivity analysis, and provide two examples to illustrate each method. Additionally, we provide a carry-through example based upon social network analysis so that we can compare these methods.

Business Analytics and Intelligence tools (BAI) are spreading across all industries. As the amount of business data exponentially grows everyday, it is critical to have appropriate tools that make it possible to consume and take profit of this digital universe. Even though BAI tools have positively evolved in this direction, meaningful and productive use of data still remains a major obstacle for most organizations. Of drowning in data, they have moved to drown in reports, dashboards and data summaries. We believe that BAI technologies should evolve towards a more holistic approach in which business users can focus on business concepts and questions, without wasting time in lower levels of cumbersome data manipulation. We propose the Business Analytics Architecture (BAA) as the infrastructure supporting ‘smart’ and enterprise BAI operations. It enables users to define the business concepts they want to focus on, as well as connecting them with data at storage level. Analytical and data-mining algorithms are intensively exploited, all guided by the ‘semantic layer’ previously depicted by business users. BAA integrating up-to-date data mining and artificial intelligence techniques as well as some well-known business practices such as Balanced Scorecard and Strategy Maps.

Considering the reliability of an area traffic control road network, most travel delay is directly dependent on correct operation of signal settings. The purpose of this paper is to devise an efficient scheme to evaluate the reliability of a signal-controlled road network. A min-max complementarity problem is proposed to characterize user equilibrium flow in the presence of a worst-case disruption of given link capacity loss. A computationally tractable solution scheme is proposed to identify important links whose disruption could cause substantial increase in travel delay to all road users. Numerical computations are conducted in a medium-sized road network to demonstrate the feasibility of the proposed solution scheme. The results indicate that the most critical signal-controlled traffic streams can be conveniently identified, when failed to perform its normal functions, would give rise to maximum travel delay to all road users.

Business development requires technologically reliable products developed through excellence in project management. This excellence is obtained with advanced project control that should include Earned Value Management (EVM) methodology and project objectives accomplishment orientation. In this work, an analytical model to implement the project objectives control with the EVM is presented. The objectives are periodically measured along the project life with their weights and impact at the end of the project, and then, affecting to the earned value. This provides early indications not only of the project progress but also of the project objectives accomplishment, and highlights the possible need for corrective actions. The analytical model also considers the forecasting of the objectives and their limits at project completion. The model is applied to a case study of engineering product development focusing on getting technical objectives. The generality of the model permits to apply it to any type of project, small or large, in any industry and with any kind of objectives either technical, commercial, economic, etc.

Maturity models can be defined as approaches to improving the business process management (BPM) of any organisation, or, from a global system-wide perspective, the organisational processes.

The rationale behind the concept of maturity is that the organisations with experience carry out tasks systematically, where immature organisations achieve their outcomes as a result of considerable efforts of individuals using approaches that they create more or less spontaneously. Nowadays maturity models are indissolubly linked with the Process Maturity Models, as conceptual models that compares the maturity of organisation current practices against an industry standard. These models support any organisation to set priorities for improving the product/service operations in order to find the optimum levels of efficiency and effectiveness.

On the other hand, Excellence Models provide a holistic view of the organisation and it can be used to determine how these different methods fit together and complement each other. Any Excellence Model can therefore be used in conjunction with any number of these tools, including BPM, based on the needs and function of the organisation, as an overarching framework for developing sustainable excellence. In fact, one of the eight fundamental concepts of the European Foundation for Quality Management (EFQM) Excellence Model is “Managing with agility”, principle based on that excellent organisations are managed through structured and strategically aligned processes using fact-based decision making to create balanced and sustained results.

The structure of Excellence Models, in the case of the EFQM Excellence Model, includes the following criteria: Fundamental Concepts of Excellence; Model Criteria and; RADAR Logic. They allow to introduce a more complex concept about maturity in the management and not only in processes.

This chapter describes a new point of view of the concept of maturity model, introducing new evaluation elements beyond the concept of process.

This research gives an overview of the Analytic Hierarchy Process (AHP) and Intuitionistic Fuzzy TOPSIS (IFT) methods. It deals with an evaluation methodology based on the AHP-IFT where the uncertainties are handled with linguistic values. First, the supplier selection problem is formulated using AHP and, then, is used to determine the weights of the criteria. Later, IFT is used to obtain full-ranking among the alternatives based on the opinion of the Decision Makers (DMs). The present model provides an accurate and easy classification in supplier attributes by chains prioritized in the hybrid model. A numerical example is given to clarify the main developed result in this paper.

The following Chapter intends to be a small guide to investing in hedge funds or a guide to take into account when trying to understand the complexities of investing in hedge funds. We aim to give a general overview of the field of alternative investments and to introduce its complexities, because investing in hedge funds is not at all a very simple task.

In this Chapter, we assess the challenges of analysing and selecting hedge funds. Alternative investment vehicles have taken an important role not only in the diversification of portfolios but also as standalone investments. Capturing the entire risk dimensions implied in hedge fund investment strategies is paramount in understanding alternative investments. We also analyse the problem of the lack of benchmarks. Should the performance of a hedge fund follow a benchmark? As absolute return vehicles, alternative investment organizations should not be benchmarked. However, investors need to compare returns with other assets in order to properly assess the cost of opportunity implied in hedge fund investing. We consider also benchmarking among peers as a new and latest strategy.

This chapter introduces functional data analysis, a relatively new technique for data analysis in Business Analytics. The distinct feature of this technique is that it deals with smooth functions or processes, which generate the discretized data sample that we observe. The functional approach allows us to flexibly model system dynamics, to analyze observations with measurement errors, and to fit data with sparse observations. We illustrate the application of functional data analysis in the capital structure of California hospitals. We also point out the functional data analysis application in business research and future research directions.

We present a software application developed to optimize the annual planning of visits of a brewing company’s sales/marketing staff to their customers. Each of these customers must be annually visited a provided number of times. Thus, each salesperson is assigned to a set of customers that must be visited each week. The application will assign all the visits of a salesperson to each customer so that all weeks should have more or less the same number of visits. By virtue of this approach, the brewing company diminished their marketing operating costs, as well as improved their customer relationships.