金融大数据分析教学大纲英文版.docx

《金融大数据分析教学大纲英文版.docx》由会员分享，可在线阅读，更多相关《金融大数据分析教学大纲英文版.docx（12页珍藏版）》请在淘文阁 - 分享文档赚钱的网站上搜索。

1、Syllabus of Financial big data analysisCourse Name： Financial big data analysis Course Code：Credits： 2Total Credit Hours： 32Lecture Hours： 20Experiment Hours：Programming Hours ： 12Practice Hours ：Total Number of Experimental (Programming) Projects,Where, Compulsory (), Optional ().School： 08School o

2、f BusinessTarget Major： FinanceI、Course Nature & AimsThe aim of this course is to provide students with a critical and practical appreciation of how data, computing and artificial intelligence technologies can be used and developed to deliver value in organisations with finance, risk and decision-ma

3、king related digitalisation from both technology and business perspectives. The course applies principles of financial economics and practical programming/machine learning and big data analysis to help students in finance focus on solving real problems and developing the skillsets that are relevant

4、for employers now and in the future.II、Course Objectives1. Moral Education and Character Cultivation.Financial big data analysis requires students to have a comprehensive understanding of financial data, typically the financial big data analysis. This course helps students establish a critical and s

5、cientific appreciation of modern technologies to deliver the challenges faced by future financial professionals in China. The socialist core value education will be combined in the teaching content to guide and highlight the positive value, knowledge and laws in modern fintech.2. Course ObjectivesTh

6、rough the study of this course, students1 qualities, skills, knowledge and abilities obtained are as follows：Objective 1. Students can master the basic methods of financial data analysis, learn several important data mining methods, and understand how to use computing software to analyze data, solve

7、 problems and complete relevant research, (corresponding to Chapter 1,2 and 3, supporting for graduation requirements index 2.1)Objective 2. Students can understand the important application of data analysis and data mining in finance to establish an understanding of the data analysis and data minin

8、g methods. Students can use basic research methods to conduct simple financial research, (corresponding to Chapter 4, 5, 6, 7 and 8, supporting for the graduation requirements index 4.3)Supporting for Graduation RequirementsObjective 2 (Index 4.3)Through the study of this course and the use of relev

9、ant software, students can understand the important application of data analysis and data mining in the financial field, so that they can use the data analysis and data mining methods they have learned to carry out applied research in the financial field, and have the foundation and ability to furth

10、er study.5153050Total103060100WI、Course ResourcesTextbooks：Zhang Yaoting et al. Introduction and application of data miningfM, Beijing, China statistics press, 2001.Bibliography：1. Michael and Jin Ma: a complete collection of financial research methodologyM, Beijing, Tsinghua university press, 2005.

11、Reading Materials： NoIX、NotesPrerequisites: Statistics, Probability and mathematical statistics, Econometrics, Microeconomics,Macroeconomics and securities investmentFollow-up Courses: Corporate governance, financial engineering, fixed income securitiesContents and Requirements of Students* Self-stu

12、dy: NoneBilingual Teaching or Not: NoRequirements and Proportion of Bilingual Teaching: NoneDiscipline and Considerations of Practice Session: No practice session.Notes: NoneAuthor：Approved by：The graduation requirements supported by course objectives are mainly reflected in the graduationrequiremen

13、ts indices 2.2 and 4.3, as follows:Supporting for Graduation RequirementsCourseObjectivesGraduationRequirementsIndices and Contents Supporting for GraduationRequirementsTeachingTopicsLevel ofSupportIndicesContentsObjective 12. ComprehensiveknowledgeIndex2.2:Understand the concept of finance and its

14、embodiment in specific fields; analyze and deal with the basic financial business.Chapter1,2,3HObjective 24. Practical abilityIndex4.3:Able to use professional theoretical knowledge and modern economic research methods to analyze and solve practical problems, with certain scientific research ability

15、.Chapter456,7,8M田、Basic Course ContentThis course is delivered through 9 lectures and 6 programming lab sessions with a total of 32 credit hours.Chapter 1 Understanding financial data (supporting course objectives 1)Quantitative data1.1 Data mining, a new method of mining knowledge from massive data

16、Disciplines involved in data mining1.2 Recent development and application fields of data mining technologyTeaching Requirements: The main content is a quantitative data, data mining and its application involves the main subject areas and fields. Students are to learn the quantitative data and the co

17、ntent of data mining. The learning content involves the main subject in the field of data mining, requires students to understand relevant knowledge of financial data types, collection methods and corresponding software in processing data acquired.Key Points： The concept of data mining, the main fun

18、ction of data mining, and the basic method of data processing.Difficult Points： Data processing methodMain functions of data mining (supporting course objectives 1)2.1 Classification and prediction of dataSequence discovery2.2 Characterization, comparison and association rule of data miningCluster a

19、nalysisTeaching Requirements: The main content is the function of data mining. In this chapter, students are required to learn the content of classification and prediction, sequences, the characterization, comparison and association rule of data mining, and cluster analysis. Students are required to

20、 learn relevant knowledge and understand main functions of the data mining, the basic types of financial data, financial data collection method, and learn to use corresponding software to preliminary processing of import data to analyze and resolving problems.Key Points： The concept of data mining,

21、the main function of data mining, and the basic method of data processing.Difficult Points： The basic method of data processing.Chapter 2 Data mining software (supporting course objectives 1)R language3.1 Application of R language in financial time seriesApplication of R language in financial data m

22、iningTeaching Requirements: This chapter introduces R language, the application of software in financial data mining. Students are required to learn R language and its application in financial time series analysis and data mining. Students are required to understand relevant knowledge, the data acqu

23、isition, data processing and etc. Students are expected to understand the basic types of financial data, learn financial data collection method, and use the corresponding software to preliminary processing of import data.Key Points； The concept of data mining, the main function of data mining, the b

24、asic method of data processingDifficult Points： The basic method of data processing.Chapter 3 Discriminant analysis (supporting course objectives 2)Statistical principle of discriminant analysis4.1 Assumptions, data requirements and software implementation methods of discriminant analysisCase I: Con

25、struction of enterprise financial distress prediction model based on discriminant analysisTeaching Requirements: This chapter introduces discriminant analysis. Students are required to learn statistical principle of discriminant analysis, discriminant analysis and the assumptions, data requirements

26、and the software realization method as well as the enterprise financial distress prediction model based on discriminant analysis to build the case. Students are required to understand the basic statistical analysis methods of forecasting and data mining technology to understand all kinds of methods

27、and techniques of theoretical basis, using conditions and the software realization method. Students are expected to use one or more classification and prediction methods, through the calculation of software and actual data to build the bank borrower default prediction model or default probability pr

28、ediction model, or credit card fraud prediction model.Key Points： Realization methods of classification and prediction in data mining.Difficult Points： Statistical analysis of principles.Chapter 4 Logistic regression and Probit process (supporting course objectives 2)Statistical principles of Logist

29、ic regression5.1 Software implementation method of Logistic regressionStepwise Logistic regression5.2 Statistical principle and software implementation method of Probit process5.3 Case 2: Establishment of enterprise financial distress prediction model based on Logistic regression and Probit processC

30、ase 3: Prediction model of borrower default probability based on Logistic regression and Probit processTeaching Requirements: This chapter introduces Logistic regression and Probit process. Students are required to understand Logistic regression statistic principle, the prediction of variables selec

31、ted in software of Logistic regression. Students are required to learn basic statistical analysis methods of forecasting and data mining technology, understand all kinds of methods and techniques of theoretical basis under each condition and can apply simple codes in using software to solve for clas

32、sification and prediction methods. Students can use software calculations to build the bank borrower default prediction model, default probability prediction model, and credit card fraud prediction model.Key Points： Realization methods of classification and prediction in data mining.Difficult Points

33、： Statistical analysis of principles.Chapter 5 Decision number classification prediction method (supporting course objectives 2)Entropy and information increment6.1 Construction principle and prediction criterion of decision numberSoftware implementation method of decision number classification pred

34、iction6.2 Case 4: Construction of credit card fraud warning system based on decision tree methodTeaching Requirements: The students are required to understand the classification and prediction method. Information entropy increment, the number of decisions to build and decision-making theory and crit

35、erion for classification prediction method of software realization, and the credit card fraud warning system based on decision tree method to build the case are delivered. Students are required to understand the basic statistical analysis methods of analysis and forecasting, and data mining technolo

36、gy, understand all methods and techniques of theory and apply software realization method. Students are expected to learn one or more classification and prediction methods to build the bank borrower default prediction model, default probability prediction model, and credit card fraud prediction mode

37、l.Key Points： Realization methods of classification and prediction in data mining.Difficult Points： Statistical analysis of principles.Chapter 6 Selection of predictive variables and signal-noise analysis (supporting course objectives 2)Method for the determination of the information content of vari

38、able-prediction-signal noise analysis7.1 Signal-software implementation method of noise analysisNecessity of variable transformation and construction of comprehensive predictors7.2 Case 4: Establishment of an early warning model of currency crisis based on signal-noise analysisTeaching Requirements:

39、 Students are to predict the selection of variables and signal-noise analysis. They are expected to learn the determination method of signal analysis, noise and learn signal - noise analysis software implementation method, the necessity of the variable transformation and comprehensive prediction ind

40、ex construction, and methods based on signal - noise analysis with the case of currency crisis early warning model building. Students are to build the basic statistical analysis methods of analysis and forecasting, and data mining technology, understand all kinds of methods and techniques of theoret

41、ical basis, using conditions and the software realization method. They are also expected to master the use of one or more classification and prediction methods, through the calculation of software and actual data to build the bank borrower default prediction model, default probability prediction mod

42、el, and credit card fraud prediction model.Key Points： Realization methods of classification and prediction in data mining.Difficult Points： Statistical analysis of principles.Chapter 7 Mining of sequence data (supporting course objectives 2)Concepts of time series data and sequence data8.1 Trend an

43、alysisSoftware implementation method of trend analysisTeaching Requirements: Students are expected to predict the selection of variables and signal-noise analysis, Students are required to learn time-series data, the concept of sequence data, trend analysis and the software implementation method of

44、learning trend analysis. It requests the students to understand the concept of sequence found, similarity measurement method, sequence detection software implementation approach, the sequence found application in the financial sector. Students can understand the use of sequence found the concept and

45、 application of data mining software realization in the financial sector.Key Points： Sequence discovery and similarity measurement in time series and the application in the financial field.Difficult Points： Trend analysis and the mastery of similarity measurement.Chapter 8 Sequence discovery and its

46、 applications (supporting course objectives 2)9.1 What is sequence discoveryMeasurement of similarity9.2 Software implementation of similar sequence discoveryCase 5: Mining of stock market trading decision rulesTeaching Requirements: Students are expected to learn what is sequence discovery, the sim

47、ilarity measurement method, the software realization, and the stock market trading decision rules mining case. Students are required to understand the concept of sequence found, similarity measurement method, sequence detection software implementation approach, the sequence found application in the

48、financial sector, so that the students can use the sequence found the concept and application of data mining software realization in the financial sector.Key Points： Sequence discovery and similarity measurement in time series and the application in the financial field.Difficult Points： Trend analysis and the mastery of similarity measurement.IV、Table of Credit Hour DistributionTeachingContentIdeological and Political IntegratedLectureHoursExperimentHoursPracticeHoursProgrammingHoursSelfstudyHoursExerciseClassDiscussionHoursChapter 1:Understanding financial dataFinancial big data tre