SOLUTION: Advanced Decision Making | My Assignment Tutor

Assessment Module Title:Advanced Decision Making: Predictive Analytics and Machine Learning.ModuleCode: DS7003Level:7 Credit:30 ECTScredit:15Module Leader: Dr Yang Li Assessmentmethodswhichenablestudenttodemonstratethelearning outcomesfortheModule:Coursework Utilise a negotiated case study and related problem to analyse decision-making solutions (5,000 words equivalence + graphics, charts, maps, scripts etc.).Weighting:100%LearningOutcomesdemonstrated:All DecisionMakingProject This carries 100% of the marks for this Module. Pass mark for this module is 50% You will work on a project individually. Through your project you should demonstratecompetencein using machine learning for classification, regression or time series using R. Machine Learning: you should choose a dataset from the UCI Machine Learning Repository at http://archive.ics.uci.edu/ml/datasets.html except those featured in Lantz (2013) as listed below1 which are disallowed. Where a student has identified a suitable dataset for machine learning from another source, they should get approval from the module leader. You should carry out and compare contrasting two methods (e.g. regression tree vs. ANN) of supervised learning or temporal forecasting in order to achieve a best possible result from the modelling. The project report should provide the reader with a clear understanding of the background and theoretical positions underscoring the analysis, a justification for the form of analysis undertaken and techniques used, and an evaluation and presentation of the results. There should be a list of references set out according to accepted academic conventions. Your report should include the following sections: a title;an abstract (and for joint projects, a summary of your contribution to the work);a introduction including an explanation of the background to the topic and review of relevant literature;a critical summary of your overall methodological approach;a description of your data sources and what the data consist of (exploratory analysis);a presentation of your ML analysis, outcomes and their evaluation or sensitivity analysis;a concluding discussion of the findings, a critical reflection/comparison of the techniques used;a list of references in Harvard style;an appendix of R scripts for key parts of your analysis. 1 Excluded data sets are:38. Breast Cancer Wisconsin (Diagnostic)64. Concrete Slump Test235. Semeion Handwritten Digit39. Breast Cancer Wisconsin (Original)74. Credit Approval244. SMS Spam Collection40. Breast Cancer Wisconsin (Prognostic)152. Letter Recognition248. Spambase48. Challenger USA Space Shuttle O-Ring 63. Concrete Compressive Strength178. Mushroom 227. Iris301. Wine Quality Dates: Friday 5th March 2021: a short one-pager setting out your choice of which data set from the UCI Machine Learning Repository will be used in R and which techniques are going to be applied and compared. To be submitted through the Moodle dropbox as a Word file named with you student ID in the form u123456_DS7003_plan.docx. Friday 23rd April 2020: a preliminary draft of your report through the Moodle dropbox in a Word file named with you student number in the form u123456_DS7003_draft.docx Friday 14th May 2020: your final report, first through the Turnitin dropbox to self-check for inadvertent plagiarism, and then through the Final Assignment dropbox in Moodle as a Word file named with you student number in the form u123456_DS7003_final.docx Theassignmentmustbe submittedthroughMoodlebeforemidnightonthedue date. Annex1:ModuleSpecification ModuleTitle:ModuleCode:DS7003ModuleLeader:Advanced Decision Making: Predictive Analytics & Machine LearningLevel:7 Credit:30ECTScredit:ProfessorAllanBrimicombeAdditional tutor: Dr YangLiPre-requisite:NonePre-cursor:NoneCo-requisite:NoneExcludedcombinations: NoneSuitableforincomingstudyabroad?NLocation of delivery:UEL – Block delivery of face-to-face teaching and practical sessions with on-linesupportfor learningandprojectwork.Summaryof moduleforapplicants:This module aims to develop a deep understanding of ways of making decisions that are based strongly on data and information. Particular focus will be on mathematical, statistical and algorithmic-based decision-making models using predictive analytics and machine learning. Various cases will be examined. The software environment will be predominantly open-source R.Maintopicsof study:Models used in decision-making Mathematics and statistical foundations of decision-making Principles of algorithm-based models Use of predictive analytics and machine learning in decision-making Analysis of case studies Assessment of accuracy, propagation of uncertainty and probabilities of uncertain events Utility vs. cost benefit/effectiveness Maximisation of expected utility of modelsThis module will be able to demonstrate at least one of the following examples/ exposures(please tick one or more of the appropriate boxes, evidence will need to be provided later in thisdocument)Live,applied project☒ Company/engagementvisits ☐ Company/industrysectorendorsement/badging/sponsorship/award ☐LearningOutcomesfor themodule Please use the appropriate headings to group the Learning Outcomes. While it is expected that amodule will have LOs covering a range of knowledge and skills, it is not necessary that all fourheadings are covered in every module. Please delete any headings that are not relevant. You shouldnumberthe LOs sequentiallyto enablemapping ofassessmenttasks.Where a LO meets one of the UEL core competencies, please put a code next to the LO that links to thecompetence.DigitalProficiency–Code=(DP) Industry Connections –Code=(IC) EmotionalIntelligenceDevelopment–Code=(EID) SocialIntelligenceDevelopment–Code=(SID) PhysicalIntelligenceDevelopment–Code=(PID) CulturalIntelligenceDevelopment–Code=(CID) Community Connections–Code=(CC) UELGive-Back–Code= (UGB) At the end of this module, students will be able to:KnowledgeHave a deep understanding of mathematical, statistical and algorithm-based decision-making (IC)ThinkingskillsDesign and implement decision-making models (DP, PID) Assign probabilities to uncertain events; cost-benefits to possible consequences; and making decisions that maximize expected utility (IC, EID)Subject-basedpracticalskillsUse machine learning in R and other decision-support tools (DP) Critically evaluate alternative decision models and their comparative accuracy (IC)Skillsforlifeandwork(generalskills)Conduct real-world projects using machine learning and predictive analytics (DP, PID) 7 Critically evaluate and analyse data and the accuracy of models (DP, EID) 8 Able to communicate machine-learning projects through well-crafted reports (SID, CID)Teaching/ learning methods/strategies used to enable the achievement of learning outcomes:Foron campusstudents:Integrated lectures and practical workshops with live demonstration of techniques that students follow on their own laptop. Extensive use is made of the University’s virtual learning environment. Feedback is provided throughout the module in the form of both formative and summative work.Assessmentmethodswhichenablestudentstodemonstrate the learning outcomes for themodule;pleasedefineas necessary:Coursework Utilise a negotiated case study and relevant techniques to analyse decision-making solutions (5,000 words equivalence).Weighting:100%Learning Outcomesdemonstrated:AllIndicativereadingandresourcesforthemodule:Brimicombe, A.J. (2010) GIS, Environmental Modelling and Engineering. 2nd Edition. CRC Press, Boca Raton, FL*. Chatterjee, K. & Samuelson, W. (2014) Game Theory and Business Applications. Springer*. Chiu, Y-W. (2015) Machine Learning with R Cookbook. Packt Publishing. https://www.packtpub.com/ Doumpos, M. & Grigoroudis. (2013) Multicriteria Decision Aid and Artificial Intelligence Links, Theory and Applications. John Wiley& Son, Hoboken*. Duggan, J. (2016) Systems Dynamics Modelling with R. Packt Publishing. https://www.packtpub.com/ Fitzgerald, S.P. (2002) Decision Making. John Wiley& Son, Hoboken*. Hastie, T., Tibshirani, R. & Friedman, J. (2009) Elements of Statistical Learning: data mining, inference and prediction. Springer. Available at: http://statweb.stanford.edu/~tibs/ElemStatLearn/ Lantz, B. (2015) Machine Learning in R. 2nd Edition. Packt Publishing. https://www.packtpub.com/ O’Reilly Media (2017) Artificial Intelligence Now. O’Reilly. https://learning.oreilly.com/library/view/artificial-intelligence-now/9781492049210/ Raydugin, Y (2013) Project Risk Management Essential Methods for Project Teams and Decision Makers. John Wiley& Son, Hoboken*. Saltelli, A.; Cahn, K. & Scott, E.M. (2008) Sensitivity Analysis. John Wiley& Son ISBN 0471998923 Sanderson, C.J. (2006) Analytical Models for Decision Making. Open University Press*. Valient, L. (2013) Probably Approximately Correct. Basic Books, New York. ISBN 9780465060726 Wiley, J. (2016) R Deep Learning Essentials. Packt Publishing. Available from: http://pzs.dstu.dp.ua/DataMining/bibl/practical/R%20Deep%20Learning%20Essentials.pdf Zhao, Y. (2012) R and Data Mining: Examples and Case Studies. Elsevier. Available from: http://www.rdatamining.com Zheng, A. (2015) Evaluating Machine Learning Models. O’Reilly, https://learning.oreilly.com/library/view/evaluating-machine-learning/9781492048756/?intcmp=il- data-free-lp-lgen_free_reports_pageProvide evidence of how this module will be able to demonstrate at least one of the followingexamples/exposuresLive, applied projectIndividual data mining based around a topic from online data repositories orworkplacesCompany/engagementvisitsCompany/industrysectorendorsement/badging/sponsorship/awardIndicative learningand teaching time(10hrspercredit):Activity1. Student/tutor interaction:Activity and hours (Defined as lectures, seminars, tutorials, project supervision, demonstrations, practical classes and workshops, supervised time in studio/workshop, fieldwork, external visits, work based learning (not placements), formative assessment) :Lecture/seminar/practicals: 36 hours On-line discussion of formative feedback and direction: 4 hours2. Student learning time:Activity (e.g. seminar reading and preparation/assignment preparation/ background reading/ on-line activities/group work/portfolio/diary preparation, unsupervised studio work etc):Individual project work: 140 hours Completing worksheets of lab exercises: 40 hours Reading for the main topics of study: 80 hoursTotal hours :300hours Annex 2: Submission to Turnitin of Work Submitted for Assessment Turnitin is an internet-based text matching service that has been developed by a commercial company. It is used, under license, by most UK Universities, including the University of East London. Work that is submitted to Turnitin generates a Turnitin Originality report, showing which parts of it have been reproduced from which sources. The system compares submissions to material that is to be found: on the world-wide web; in its database of previous submissions; and in its growing number of databases of published articles. You should not assume that a Turnitin Originality report with a low similarity index is evidence that the piece of work concerned is free from plagiarism. Our policy on the use of Turnitin recognises the educational desirability that all of our students should enjoy the opportunity to self-submit their work to Turnitin (before submitting for assessment). We also recognise that Turnitin Originality Reports will sometimes assist in the identification of plagiarised work submitted for assessment. Our policy provides that a Module Leader may decide, in accordance with the policy of the appropriate School, that all student submissions for a particular component of assessment should be submitted to Turnitin, provided that the relevant Module Guide includes a notice to that effect. Notice is hereby given that all submissions for coursework of this Module must be submitted to Turnitin. Detailed guidance on how to submit your work to Turnitin can be found on this Module’s Moodle site. If you fail to submit coursework, to Turnitin, in accordance with the guidance on the Moodle site, you will be awarded a mark of 0 for the component. If you have any questions about Turnitin, you should visit the Turnitin module in UEL Moodle or go to https://www.turnitin.com. If you have any further questions, please contact UEL Compliance Team.