The following description specifies the programme curriculum offered by the Department of Computing and Decision Sciences for students who pursue the programme on a full-time 4-year basis. Flexibility is allowed for completing the programme in a longer or shorter period in accordance with the stipulations of the Regulations Governing Undergraduate Studies.
This course is designed for students to provide an introduction to data science in the digital age. Data science concerns using data to understand and analyse actual phenomena. The course covers basic IT skills, such as computer programming to assist data manipulation, data analysis and data communication. Turing award winner Jim Gray predicts that data science will be a “fourth paradigm” of science, which is data-driven and can be differentiated from empirical, theoretical and computational paradigms. Students will learn the fundamentals and appreciate the importance of data science.
The first half of the course is about learning the programming language. The topics will include: the basic Python language syntax, variable declaration, basic operators, program flow and control, Python data structures, defining and using functions and recursion, file and operating system interface. In the second half of the course, basic Python packages designed for data science will be introduced, such as NumPy, SciPy, Pandas, and Matplotlib.
Calculus plays an important role in the understanding of today’s world. This is an introductory course that presents the ideas and techniques of calculus using an informal, intuitive and geometric approach. Students need to learn both differential calculus and integral calculus and their applications to real-life situations in business, economics, the social sciences, natural sciences and visual arts. This course will equip students with the calculus background required for further study in many disciplines.
(Note: Students should take CDS1002 Calculus previously or take both this course and CDS1002 Calculus in the same term)
Probability and Statistics are fundamentals of quantitative analysis. This course introduces the basic theory of probability and statistics to students. It provides a strong mathematical background for students to understand the quantitative techniques used in the analysis of practical problems across different disciplines. Emphasis is placed on the underlying mathematical theories of probability and statistics. The topics covered include descriptive statistics, basic probability, probability distributions, correlation and the use of statistical software for data science.
(Prerequisite: CDS1003 Probability and Statistics 1 or BUS1102 Statistics for Business)
Probability and Statistics are fundamentals of quantitative analysis. This course covers statistical techniques for inferential statistics, such as estimation and hypothesis testing for population parameters. The topics covered include point estimate and interval estimate of population parameters, comparing means, non-parametric techniques and the use of statistical software for data science.
(Prerequisites: CDS1001 Introduction to Programming for Data Science)
Artificial intelligence is the study of intelligent agents. Due to the continued success of applying artificial intelligence to different challenging problems requiring high-level intelligence, there is an explosive interest in this field for scientists, dreamers, entrepreneurs and educators. This course is designed for students to understand and appreciate the basic principles of artificial intelligence. It covers computational intelligent systems, which can support decision making, interact with humans, navigate vehicles and achieve many other interesting and useful tasks. These intelligent systems are extremely useful in business, science, the humanities and other fields.
This course focuses on basic Linear Algebra used in econometrics and in social research. It will cover some basic techniques of matrix arithmetic and algebra, and in particular matrix multiplication and solution of linear equations.
View Course Details at https://www.ln.edu.hk/econ/upload/ln_econ/download/ssc2113%20course%20outline%20202009.pdf
(Prerequisite: CDS1001 Introduction to Programming for Data Science)
Computer algorithms manipulate data. A good data structure design allows algorithms to perform efficiently. Object-Oriented programming is a programming paradigm based on the concepts of “objects”, which are data structures that can exhibit “behaviour”. Students will learn the basics of data structures for various algorithms and design software using object-oriented programming.
(Prerequisites: CDS1003 Probability and Statistics 1 or BUS1102 Statistics for Business)
Organisations often need to make decisions in their best interests in various situations. This course provides an introduction to modelling, analysing and solving decision problems under certainty and uncertainty. Students will develop the concepts of spreadsheet modelling, optimisation and uncertainty, and learn how to apply quantitative techniques of optimisation and decision-making under uncertainty and forecasting to solve a variety of problems that arise in business settings. Microsoft Excel will be used to model and solve most of these problems. Through practising these techniques and Excel functions, students are expected to develop basic analytical skills and managerial insights, and also acquire competency in Excel.
(Prerequisite: CDS2003 Data Structures and Object-Oriented Programming)
This course is designed to introduce the concepts and principles of database and data warehouse. Various types of databases will be thoroughly discussed in this course, such as objected-oriented, relational, document-oriented, graph, NoSQL, and New SQL. Popular database management systems such as Microsoft SQL Server and/or Oracle will be described and implemented. Topics include data models (ER, relational, and others); query language (Structured Query Language); implementation techniques of database management systems (index structures and query processing); management of semi-structured and complex data; distributed and NoSQL databases; the dimensional modeling technique for designing a data warehouse, and data warehouse architectures, OLAP and the project planning aspects in building a data warehouse.
(Prerequisites: CDS1003 Probability and Statistics 1 or BUS1102 Statistics for Business or CLD9003 Statistics in Modern Society)
This course is designed for Data Science students. They are required to have previous knowledge of probability and statistics. Simulation is a commonly used and practical technique for modelling and analysing real operating systems to make more effective decisions. Examples of such systems include transportation, supply chain networks, job flow, airports, banks, ocean terminals, information systems, emergency response systems and human behaviour in a social network. Due to the considerable complexity of real systems, many people and organisations find it difficult to investigate human activities, manufacturing and service designs and processes without a computer simulation model. More than 89% of Fortune 500 firms have used simulation for system improvement and have experienced the benefits for a long time. This course is designed to introduce basic concepts of system modelling and computer simulation. The process and methodology of using simulation for problem solving and decision making are emphasised. Moreover, the course assignments involve the use of the simulation language “Arena”. Some of the assignments may require the ability to write computer programs in a language of the student’s choice or the use of a spreadsheet.
(Prerequisites: CDS2001 Probability and Statistics 2, CDS2002 Introduction to Artificial Intelligence and SSC2113 Linear Algebra)
This course is designed to introduce methods in machine learning (i.e., the study of how to create a machine that is capable of improving its performance in some tasks, such as perception, cognition and action, by learning from experience and data). This makes computers more intelligent. Machine learning is a powerful tool for recognising hidden and potentially useful relationships in data. It is essential in many organisations, as they can generate huge amounts of data in their daily operations and machine learning enables them to discover important knowledge from this data. The students will learn some powerful software packages for performing machine learning and apply these packages to handle different kinds of problems.
(Prerequisite: CDS2002 Introduction to Artificial Intelligence)
Data mining is an important component of data science that discovers knowledge from huge databases. Data mining is an interdisciplinary field, integrating statistics, pattern recognition, neuro-computing, machine learning and databases. It is also one of the fundamentals to extracting interesting knowledge (domain-specific rules, patterns, constraints and regularity). Students will learn the basic principles and core ideas of data mining. This course also covers many data mining approaches to discovering knowledge from a vast amount of valuable databases in business, finance, urban and medicine. Quantitative analytical skills are taught to interpret data mining models. Current IT skills are also covered in the course.
(Prerequisites: CDS3001 Databases and Data Warehouses and CDS3004 Data Mining)
Data science is the study of where information comes from, what it represents and how it can be turned into a valuable resource in the creation of business and IT strategies. Mining large amounts of structured and unstructured data to identify patterns can help an organization rein in costs, increase efficiency, recognize new market opportunities and increase the organization's competitive advantage. This course elaborates on data science problems in science, social science, arts and business. The appropriate methods of delivering data science results to different domain users and the right processes for deploying results in information and/or intelligent systems are described. Practitioners in different fields, such as marketing and finance, will be invited to share their experience in applying the data science approach to solve their problems.
The principles of project management, largely developed and tested on engineering projects, are being successfully applied to projects of all sizes and types in all fields. Furthermore, the role of project management in a cross section of applications, such as IT, product development and construction, is now emphasised. This course addresses the fundamental principles of project management and the tools and techniques at our disposal to help achieve our goals. The topics covered include project definition and start up; project attribute estimation; planning and scheduling; resource selection and allocation; implementation; post-project evaluation; project management as a career; skills and knowledge required by professionals, such as decision making and resource allocation appropriate to project phases; integration with other disciplines, such as accounting and finance. The Microsoft Project software tool will be introduced for project scheduling and management.
(Pre-requisite: CDS1003 - Probability and Statistics 1 or BUS1102 - Statistics for Business)
Marketing is evolving from an art to a science. Many firms collect massive information about consumers’ choices and how they react to marketing campaigns, but few firms have the expertise to intelligently act on such information. This course introduces students to state-of- the-art marketing analytics and demonstrates how to practically apply these analytics to real- world business decisions. The purposes of this course are to (1) present various marketing analytics that aid students in interpreting data from various sources, such as customer transactions and social media, (2) introduce some commonly used marketing analytics, such as RFM, Customer Lifetime Value and Sentiment Analysis, and (3) enable students to gain the competency to interact with and manage a marketing analytics team.
View Course Details at https://www.ln.edu.hk/mkt/courses/mkt3006/mkt3006cs.pdf
(Prerequisite: CDS3001 Databases and Data Warehouses)
Companies need to have more efficient systems to support their decision-making. This is critical to their competitiveness, and has become a critical component of their business strategy. Generally, large organizations have a vast and complex landscape of systems. More often than expected, such companies have multiple and silo-based business systems to support their operations, finance, accounting, and analytical business processes. As the scale of systems in an organization’s landscape increases, the complexity for managing the underlying data becomes even more complicated. This course covers the essential concepts, options and best practices for data administration, data protection, privacy control, user security and management, system configurations and data activity and status monitoring. The focus is on issues and principles of managing organizational data. Students will get extensive experience in developing data models, creating relational databases, and formulating and executing complex queries.
(Prerequisites: CDS3001 Databases and Data Warehouses and CDS3004 Data Mining)
This course provides an opportunity for students to integrate their knowledge obtained in other courses in a data science process that involves the preparation, analysis, reflection and dissemination of data in a chosen application setting. The emphasis is on the management and execution of a well-defined project of a suitable scale. Such projects may involve either real-world or experimental data and students may engage in such projects individually or in groups.
(Prerequisite: CDS3004 Data Mining)
(a) ECO2101 Introduction to Economics, or Level 3 or above in HKDSE Economics, or BUS2105 Microeconomics for Business, and
(b) ECO3105 Introduction to Statistics and Econometrics (from 2019-20)/Introduction to Econometrics (in 2018-19 or before) (recoded from ECO3101 from 2017-18), or ECO3104 Quantitative Methods in Economics (recoded from ECO3102 from 2017-18), or BUS1102 Statistics for Business), or CDS1003 Probability and Statistics I)
This course introduces students to the art and science of econometric modeling as applied to economics, business, sociology, and all other branches in social sciences. Students could easily apply it to many other areas such as the natural sciences. They are going to learn how to develop, statistically test, and apply econometric models. This course emphasises intuitive understanding of econometrics, as opposed to a more abstract and theoretical approach. Hands-on experience with econometric computer software is an important part of this course.
(Remark: It is preferable for students to have taken CLD9024 Mapping Our Changing World before taking this course.)
Adopting location intelligence by analysing location-based data using a geographical information system (GIS) in business is becoming a success strategy in the competitive global economy. This course introduces students to how location-based data and information can facilitate business professionals to extract, analyse, interpret and visualise business data in maps. The traditional means of business analytics usually present results in spreadsheets, bar graphs or simple charts. Maps allow business professionals to reveal the underlying proximity relationships and trends in their data. With advances in the information and communication technology (ICT), the location-based platform of GIS is instrumental in fostering smart city initiatives to addressing issues of unplanned urbanization for sustainable urban development and better quality of life. Case studies of location-based services and GIS application examples are elaborated.
(Prerequisite: CDS3004 Data Mining)
This course provides an understanding of the concept and challenge of big data. The focus is on the data analytic techniques to tackle the V’s (volume, velocity, variety, veracity, valence, and value) in big data and how these impacts data collection, monitoring, storage, analysis and reporting. Apache Hadoop is an example a big data management system to manage and process large-scale data. The following topics across the big data domain will be introduced: distributed file systems; similarity search techniques; high-performance processing algorithms for data streams; big data search and query technology. Big data analytics applications in data science will be elaborated. Students will actively participate in the delivery of this course through assignments, portfolio development, and projects.
(Prerequisite: CDS3003 Machine Learning)
Deep learning is one of the bleeding edge technologies of machine learning. It has been used in the community and industry to solve a number of big data problems in computer vision and natural language processing. Deep learning drives improvement in the precision of medical diagnosis, enhancing digital painting and the development of self-driving vehicles. This course teaches students to understand the theoretical and technical details of deep learning and to design intelligent systems that learn from complex and large-scale datasets.
(Prerequisite: CDS2001 Probability and Statistics 2)
The stochastic process is an important tool in modelling and analysing random patterns in data science. This course aims to equip students with key concepts and theories in stochastic processes, such as sample space, probability (and conditional probability), expectation (and conditional expectation), discrete time Markov chain, continuous time Markov chain and renewal process. The course provides a rigorous development of relevant concepts and models. In addition to technical rigorousness, we want to develop our students’ ability to apply the theories and models in real applications in various disciplines. This course should help build a solid background in stochastic processes and models for students and enable them to solve real problems of a stochastic nature.
(Prerequisites: CDS1002 Calculus and SSC2113 Linear Algebra)
In a mathematical optimization problem, one seeks to minimize or maximize a real function of real or integer variables, subject to constraints on the variables. Mathematical optimization refers to the study of these problems, their mathematical properties, the development and implementation of algorithms to solve these problems and the application of these algorithms to real-world problems.
The purpose of this course is to cover the parts of calculus that are most relevant to economics and business, with an emphasis on mathematical optimization questions – finding a choice of variables that maximizes a function (e.g., utility or expected return) or minimizes a function (e.g., cost and risk) in the presence of constraints (e.g., feasibility and limited resources). This course covers foundational topics from multivariable calculus and linear algebra, topics from introductory analysis (e.g., open/closed sets, compactness, maximum theorem and implicit function theorem) and problems in unconstrained and constrained optimization (e.g., Lagrange multipliers, Kuhn-Tucker conditions and applications of convexity). Topics in linear programming and calculus of variations may also be discussed.
The upcoming intake of the students will start in September of the coming academic year.