Curriculum

Curriculum

The RSM MSc in Business Analytics and Management specialisation is one academic year’s duration. Core courses are compulsory and will be offered during the autumn semester (20 EC). Master electives (18 EC) are offered in Block 2 of the autumn semester and in the spring semester. The Business Analytics Workshop (6 EC) takes starts in January and finishes after the first block of the spring semester. During the year, students work on a master thesis project (16 EC).

Please note that certain electives may be very popular. Although we can place most students in the elective(s) of their choice, there are no guaranteed places.

    • Statistical theory is a particularly rich and well-developed language that is at the heart of the plethora of analytics methods and techniques. Assuming a basic understanding of statistical methods to represent and summarize different types of data, the different techniques to capture associations among quantities, and linear regression analysis, this course introduces advanced statistical methods and techniques required for a modern data analysis approach. In particular, it will extend the least squares methodology into the domain of general and simultaneous linear models. It will present the maximum likelihood method as a basis for binary regression models, discrete choice models, truncated models, which are widely applied in data science. Moreover, the basics of time series models will be introduced, which are central to forecasting business outcomes. These more theoretical concepts will be introduced together with the fundamentals of programming and programming environments that will allow students to solve statistical, data, or simulation problems they will encounter in their future academic or professional careers.

      Learning objectives:

      • Understand the main statistical concepts required for advanced statistical data analysis, e.g., central limit theorem, least squares and maximum likelihood, hypothesis testing, multivariate analysis, discrete response modeling
      • Understand the main building blocks of a programming language, e.g., data structures, flow control, environments;
      • Solve non-trivial statistical problems using a programming language and environment, e.g., R and RStudio
    • Data is a key business resource. Web stores such as Amazon or Coolblue use customer data to dispatch purchased products and to make recommendations of new products; banking service providers such as ING or HSBC use data for processing cash and ATM transactions and for assessing a client’s credit worthiness; manufacturers such as BMW and Tesla use data to design and produce cars and to propel self-driving cars. Often, this data is spread within the organization through multiple information systems. In order for organizations to operate successfully they need to be able to share data. Data management is the field dedicated to enabling the sharing of data such that it is available at the right time, place, user and quality. This course introduces data management topics such as database design, data modeling, data definition, metadata, master data management alongside ethical frameworks that should guide the management of data.

      Learning objectives:

      • Highlight the importance of data to the enterprise
      • Experiment with database design
      • Understand topics in data administrations: data modelling, data definition, metadata, data quality, master data management
      • Analyze the current data management environment in connection to distributed data, object orientation, unstructured data
    • Managers need to understand the world around them. They need to understand how particular actions and events lead to one another. In short, they need to understand how causes connect with their effects. A rapidly developing science of causal inference, as well as recent technical advances in experimental design, provide powerful new tools for learning about the world from data.

      This course provides an overview of the science of causal inference. It covers basic questions like what is causality? and why is causality different from correlation? It presents a formal system for expressing causal relationships among data, and determining whether these relationships can be estimated from available data. It further clarifies how these ideas connect with similar concepts from statistics and econometrics.

      When observational data are insufficient to measure a causal effect, an experiment—conducted in the field or in a more controlled setting—may provide a viable alternative. This course also provides an overview of how to design experiments to answer causal questions. Emphasis is placed on using computer simulations to design experiments, and in particular, to predict how precisely an experiment can answer its question.

      Learning objectives:

      • Express causal relationships among data using Pearl’s graphical framework, and counterfactual quantities of interest using Rubin’s potential outcomes framework
      • Understand and differentiate between statistical concepts such as correlation, conditional independence, and likelihood, and causal concepts such as randomization, confounding, and exogeneity
      • Derive conditions under which causal relationships can be estimated from data
      • Design experiments to measure causal effects
      • Simulate data correspond with an assumed causal model and use them to predict the precision of causal estimates obtained from experiments
      • Understand the problems solved by stratified randomization and adaptive experimental designs
      • Think critically about the ethical consequences of making causal claims
    • Important business decisions require a motivated logical structure that captures the main reasoning, can be convincingly communicated to stakeholders and is fit to be addressed by formal, problem-solving methods. The objective of this course is to introduce modelling concepts and techniques that can be considered the backbone of decision support systems, including mathematical modelling and Monte Carlo simulation optimization. Emphasis will be on prescriptive analytics rather than descriptive and prescriptive analytics implying that interest is not so much on what has happened in the past or what may happen in the future, but also on the actions required to achieve certain outcomes. Application of such methods and techniques can be found throughout business, but especially in marketing, operations research and finance.

      Learning objectives:

      • Structure decisions and build decision models
      • Determine optimal allocations of resources in various domains, like marketing, inventory control, distribution and portfolio management
      • Ability to perform scenario analysis, simulation analysis and risk analysis
      • Assess the sensitivity of decision outcomes for different design options and environmental uncertainties
    • The course will cover the statistical fundamentals of machine learning, the main algorithms and methods, and their applications to solve management problems.

      Learning objectives:

      • Understanding the principles, structure, and limitations of the following machine-learning algorithms
      • Apply these algorithms on actual data to address specific and real management problems

      • Assess and validate the outcome of each model using multiple metrics and be able to translate the statistical outcomes into business outcomes for different stakeholders

       

    • Marketing is the interface between the firm and its environment. It is the managerial practices that ensure customer-oriented managerial actions, including product design, pricing, market communication and product distribution, generate value for “customers”. The basic tenet is that managers should be able to justify that intended value-creation actions lead to sufficient customer responses such that they surpass the costs of these actions. For instance, advertising is usually costly for companies and marketers need to calibrate to what extent the potential revenue generated by the advertising campaign exceeds its costs. However, in practice, achieving such goal is challenging, given there are countless interacting factors that influence customer responses and not all factors are under the control of managers. To address these challenges, academics and practitioners have developed and adopted a selection of analytical tools in the form of “marketing models”, crystallized from disciplines such as economics, statistics and computer science. This course focuses on how to translate managerial problems (e.g. how to successfully design and diffuse a new product, how to price a product or service to gain short-term profits and long-term equity, how to build and manage heterogeneous and dynamic customer portfolios) into analytical problems and solve the analytical problems with various marketing models. During the course, you will work on cases where you solve real managerial problems with real data. Through these exercises, the course will show you how to understand, predict and influence customers using marketing models.

      Learning objectives:

      • To understand the three basic functions of marketing models (prediction, evaluation, optimization);
      • To know how to translate managerial problems into analytical problems;
      • To master the core of marketing models (brand choice and demand models, customer segmentation, conjoint analysis, new product diffusion etc.);
      • To apply the procedures of conducting marketing analytics with existing models;
      • To understand the procedure of developing new marketing models.

       

    • This course provides students with the foundations necessary for understanding important fields of application of data analytics: Market- and Bank-Based Financial Markets. The course starts by introducing the concepts of risk and return and how these connect in financial markets. Next, we analyze how market imperfections can give scope for profitable investment opportunities and split those out by credit and equity markets. In each of those two markets we derive a standard optimization representation both for individual investments as well as for portfolios. We link these representations to real-world applications such as platform lending, asset management, robo-advising, and high-frequency trading. As both Market- and Bank-Based Financial Markets make use of company financial information, the course will also introduce analytics techniques employed in forecasting a company’s financial performance.

    • Over the last decades, IT systems, information platforms and digital communication technologies have rapidly emerged in large parts of the economy, fundamentally changing the relations among economic actors, e.g., businesses, customers and governments. The aim of this course is to introduce essential concepts from the information systems literature (e.g., IT platforms, digital technologies) and supply chain literature (e.g., lead times, inventories, operations planning) and examine which economic forces govern digital business and what distinguishes it from the traditional business relations and operations. For example, digital technologies have led to a rapid decline in the cost of storage, computation and transmission of data, which has impacted the way how products are produced, how they travel through supply networks to their intended consumers and how they are consumed.

      Questions that will be addressed in this course include: What characterizes the production of digital goods and what impact does this have on how digital goods are sold on markets? Why are many digital markets dominated by powerful platforms, such as Google and Facebook, and what makes these platform companies different from traditional companies? What are important strategies for digital platforms to compete in markets and how should platforms be regulated by public policymakers? How have digital technologies impacted the relations within supply chains, and the economic productivity and growth at the macro-economic level? What is the likely future impact of new digital technologies such as Artificial Intelligence on the future economy?

      Learning objectives:

      • Understand the main concepts from information systems and supply chain literature
      • Understand the role of information in shaping industries and supply networks
      • Understand the main principles behind the success of digital startups
      • Use economic principles to rigorously study questions related to the digital economy and supply chains
    • In this course, students will be challenged to solve real-world problems contributed by a variety of companies in all fields of application. Not only is there a need to master analytical methodologies and programming, students also need to think about the business and behavioral aspects of the solutions they propose. This starts by a thorough understanding of the business problem at hand. Students then make a motivated choice for a methodological approach and need to find creative solutions for all kind of practical problems they encounter (such as missing data). Finally, the proposed solution needs to be presented with sufficient awareness and consideration for sensitive issues in the organization and the ethical aspects of the proposed solutions.

      Learning objectives:

      • Understand real-life business problems and associated organizational and ethical constraints
      • Select appropriate data and methodology for solving those
      • Develop hands-on implementational problem solving skills
      • Communicate proposed solutions in a way that makes acceptance and implementation likely
    • “What are your biggest strengths?”, “What motivates you?”, “Can you tell me about a difficult work situation and how you managed to overcome it?”, “How to make sure you and your collaborators finish your project on time”, “What is the greatest asset to have when you are going into a negotiation?”, “What questions do you ask in a negotiation such that you discern the other parties position and motivation?” These are important challenges for anyone’s career. This course will give you the knowledge, skills and attitude to answer these questions and others. After giving you the toolset for successfully securing a job in the field of business analytics, the course prepares you to achieve desired results in negotiation settings. Although negotiations pervade our professional and personal lives, they are extremely valuable for business analysts that are expected to work in interdisciplinary teams.

      Learning objectives:

      • Create tailored job application documents
      • Analyze strengths and weaknesses, personality, values and skills and identify career gaps and create action points to fill the gaps
      • Demonstrate written and verbal communication skills for job applications
      • Understand the recruitment and application process in business analytics industry
      • Understand and apply methods to create and claim value in negotiations
      • Apply intervention methods for enhancing negotiation performance
    • The emergence of information and data technologies, together with the sophistication of tools in econometrics and machine learning, have led to a radical shift in the way marketing operations are run. The focus of companies has been shifted away from product-centric approaches and mass marketing campaigns to customer-centric campaigns tailored to the needs and wants of each individual customer. Such campaigns target a well-chosen subset of customers, at a well-chosen time, and with a well-chosen incentive. They focus on the three stages of a customer lifecycle: customer acquisition, customer development and customer retention. This elective will provide students with the necessary knowledge and skills to tackle these challenges. The course will focus as much on the managerial questions and challenges (e.g., how to manage a portfolio of customers, how to optimize customer acquisition and retention, how to increase customer engagement, the tradeoff between proactive vs reactive strategies, win-back strategies, viral marketing and referral campaigns, …), as well as on the use of methodologies (uplift models, causal inference, probability models, boosting, bagging, decision trees, optimization methods) to address these questions. The elective will be articulated around the core metric of Customer Lifetime Value (CLV).

    • The role of algorithms in organizations is twofold: on the one hand algorithms are used to control organizations, yet on the other hand algorithms themselves need to be controlled. This elective considers both perspectives in tandem: it looks at how algorithms improve organizations’ operations while considering the levers necessary to check algorithmic decision-making. More specifically, this elective discusses the pillars of internal and management control systems, how algorithms are embedded in these systems, and what controls over algorithms can be integrated in these systems.

       

    • Consumers generate a digital footprint by using various technologies in their everyday life, such as mobile applications, internet browsers, and wearables. Marketing analysts benefit from the variety and volume of data that consumers generate online as this provides very detailed information at individual level. Such data can be used to (1) improve measurements of consumer preferences and attitudes, and (2) offer better product recommendations. Given the volume of data, analysts are often using machine learning algorithms and are primarily interested in prediction accuracy. While prediction is very valuable for businesses, understanding the drivers of consumer behavior can provide additional benefits to companies. This course starts with an introduction to theories of consumer attention, search, and choice that are used as a foundation for building advanced quantitative models and marketing strategies. Then, students learn how to combine theoretical insights with quantitative models in order to develop attribution models and recommender systems. Because digital footprints often contain personal or sensitive consumer level information, topics related to the ethical use of data and models are covered.

       

    • The financial sector has been increasingly disrupted by the use of technology. Moreover, recent regulations such as the EU PSD2 directive, have created an environment that further facilitates the use of technology, big data, and algorithms in financing applications. One can think about payment systems, Peer to Peer Lending, Crowdfunding, Crypto-currencies, Robo Advising, and High-Frequency Trading.  In the first part of the course, we discuss the possible FinTech business models and their impact on traditional players in the financial sector as well as their impact on market outcomes. In the second part of the course, we go in more detail by analyzing the problems and analytical methods of these business models in detail.

    • Social Networks shape many aspects of how people and organizations interact, take decisions, and ultimately perform. With the advent of Social Media (e.g., Facebook and Twitter) and with the increasing digitization of all forms of communication and business processes, Network Analytics has become a valued asset to better understand how different agents interact and how to best take advantage of the network structure to increase overall system performance. This course will cover the fundamentals of network science, the methods, theories, and the procedures for data collection and analysis in very large social networks. Covered topics include clustering, information diffusion, organizational design, viral marketing, social media and others.

      This course provides the basics of network data analytics, including fundamental network- and node-level metrics, as well as more advanced analysis methods, with attention to the application areas where these can and have been used. Students will engage in in-class projects in which they collect and analyze network data using the tools and methods covered in class. Students will apply these methods to specific networks, such as social media networks (e.g., Twitter), co-worker networks, organization networks, and product networks.

       

    • Recent years have witnessed dramatic changes in the ways businesses manage their supply chain operations, engendering a fundamental reliance on massive data from varied sources and advanced business analytics. New businesses have emerged with an explicit data-centric approach to supply chain operations, e.g. Amazon, Coolblue, Booking.com, while traditional suppliers (and other organizations) are heavily investing in transforming towards data-supported supply chain operations. Data about transactions and processes are central to forecasting product demand, to predict arrival times, to identify anomalies and structural changes, to monitor customer behavior or to estimate utilization rates. The analytics outcomes support operational, tactical, and strategic decision making throughout the supply chain: assortment planning, inventory management, workforce planning, procurement and production decisions, risk assessment, pricing, and the planning of logistics resources, routes or terminal capacity. Supply chain analytics is at the heart of the modern business.

      This elective will introduce modern forecasting and machine learning methods to predict supply chain outcomes. Also, it will present methods to determine optimal prices, routes and inventory levels. All discussed methods and techniques will be embedded in typical supply chain topics.