MIS771 - Descriptive Statistics and Visualisation Trimester 1, 2017 Page 1 of 11 MIS771 Descriptive Analytics and Visualisation Assignment Two Background This is an individual assignment, which requires you to analyse a given data set, interpret and draw conclusions from your analysis, and then convey your conclusions in a written technical report to an expert in Business Analytics. Percentage of final grade 35% The Due Date and Time 11.59 PM Monday 15th May 2017 Submission instructions The assignment must be submitted by the due date electronically in CloudDeakin. When submitting electronically, you must check that you have submitted the work correctly by following the instructions provided in CloudDeakin. Please note that we will NOT accept any paper copies or part of the assignment submitted after the deadline or via Email. No extensions will be considered unless a written request is submitted and negotiated with Dr Kia Kashi before Thursday 11th May 2017, 5 PM. Please note that assignment extensions will only be considered if you attach your draft assignment with your request for an extension. You must keep a backup copy of every assignment you submit until the marked assignment has been returned to you. In the unlikely event that one of your assignments is misplaced, you will need to submit your backup copy. Any work you submit may be checked by electronic or other means to detect collusion and/or plagiarism. When you are required to submit an assignment through your CloudDeakin unit site, you will receive an email to your Deakin email address confirming that it has been submitted. You should check that you can see your assignment in the Submissions view of the Assignment Dropbox folder after upload, and check for, and keep, the email receipt for the submission. MIS771 - Descriptive Statistics and Visualisation Trimester 1, 2017 Page 2 of 11 Penalties for late submission: The following marking penalties will apply if you submit an assessment task after the due date without an approved extension: 5% will be deducted from available marks for each day up to five days, and work that is submitted more than five days after the due date will not be marked. You will receive 0% for the task. 'Day' means calendar days. The Unit Chair may refuse to accept a late submission where it is unreasonable or impracticable to assess the task after the due date. For more information about academic misconduct, special consideration, extensions, and assessment feedback, please refer to the document Your rights and responsibilities as a student in this Unit in the first folder next to the Unit Guide of the Resources area in the CloudDeakin unit site. The assignment uses the file AusPaper.xlsx, which can be downloaded from CloudDeakin. Analysis of the data requires the use of techniques studied in Module-2. Assurance of Learning This assignment assesses following Graduate Learning Outcomes and related Unit Learning Outcomes: Graduate Learning Outcome (GLO) Unit Learning Outcome (ULO) GLO1: Discipline-specific knowledge and capabilities - appropriate to the level of study related to a discipline or profession. GLO3: Digital Literacy - Using technologies to find, use and disseminate information GLO5: Problem Solving - creating solutions to authentic (real-world and ill-defined) problems. ULO 1: Apply quantitative reasoning skills to solve complex problems. ULO 2: Use contemporary data analysis and visualisation tools and recognise the limitation of such tools. Feedback before submission You can seek assistance from the teaching staff to ascertain whether the assignment conforms to submission guidelines. Feedback after submission An overall mark together with suggested solutions will be released via CloudDeakin, usually after 15 working days. You are expected to refer and compare your answers to the suggested solutions to understand any areas of improvement. MIS771 - Descriptive Statistics and Visualisation Trimester 1, 2017 Page 3 of 11 Case Study (Background to AusPaper) AusPaper, a subsidery of Pinnon Paper Industries, is an Australian company with a long history in local manufacturing of paper products. In 2013 only, AusPaper produced 619,000 tonnes of paper products, and sold more than 690,000 tonnes of products to local and overseas markets. They export their products to over 75 countries in Asia, USA, Europe, Middle East, the Indian subcontinent, Latin America and Africa. AusPaper sells paper products to two market segments: the newspaper industy (e.g. Australian Finacial Review, Herald Sun etc.) and the magazine industry (e.g. Mens’ Style Magazine, Homes and Gardens etc.). Also these products are sold to these market segments either directly to the customer or indirectly through a broker. Despite their successful operations and solid financial turn-overs over the last two decade, AusPaper is forecasting a major shift in business climate within the next seven years. This is a result of a change in end-consumers preferences (i.e., readers’ preference to access newspapers, magazines online or via ereaders, and social media). Now more than ever, AusPaper management feels the need to ensure a strong customer base and ideally a strong strategic alliance with their clients in newspaper and magazine industry. In addition, they are planning to put in place a formal procedure to be able to project future financial turnovers using historical data. Consequently, AusPaper has approached ANALYTICS7 (a Market Research Company) and asked them to conduct a large-scale survey of their clients to better understand the characteristics of AusPaper customers, their perceptions of the company, and the likelihood of customers building long-term strategic alliance with AusPaper. Data Collection Process (Conducted by ANALYTICS7) To address AusPaper concerns, ANALYTICS7 has contacted purchasing managers of firms buying from Auspaper and encouraged them to participate in an online survey. The collected data are then supplemented by other information compiled and stored in AusPaper’s data warehouse and accessible through its decision support system. Primary Database (accessible via AusPaper.xlsx file) The primary databse consists of 200 observations on 18 separate variables. Two types of information are accessible in this database. The first type of information is perceptions of AusPaper’s performance on 13 attributes. Purchasing managers of firms buying from AusPaper were asked to rate the company on each of these 13 attributes using a 0 – 10 scale, with 10 being “Excellent” and 0 is being “Poor”. The second type of information relates to purchase outcomes and business relationships (e.g., satisfaction with AusPaper and whether the purchasing firm would consider strategic alliance / partnership with AusPaper). A third type of information is available from AusPaper’s data warehouse and includes information such as size of customer and length of purchase relationship, as well as quarterly turnover of AusPaper operations. A complete listing of variables, their definitions, and an explanation of their coding are provided in AusPaper.xlsx file. MIS771 - Descriptive Statistics and Visualisation Trimester 1, 2017 Page 4 of 11 Your Role as an ANALYTICS7 Data Analyst Intern You are a master of business analytics student doing an interenship at ANALYTICS7. The research team manager (Hugo Barra, with PhD in Data Science and a Master Degree in Digital Marketing) has asked you to lead the data analysis process for AusPaper project and directly report the results to him. You and Hugo just finished a meeting wherein he briefed you on key purposes of AusPaper research project. Hugo explained that an important prerequisite in building a strategic alliance in a B2B environment is “customer satisfaction” with a firm’s operations. Therefore, the first goal is to identify key factors that predict customer satisfaction with past purchases from AusPaper. He is also interested in gaining deeper insights into factors that predict the “likelihood of AusPaper customers building strategic alliance” with the firm. The final analytics goal is constructing a forecasting model to predict AusPaper’s turnover in the upcoming three quarters of 2017. From these understandings, Hugo and consequently AusPaper will be in a good position to develop plans for the next financial year. In addition to briefing you about key research questions, Hugo also allocated relevant research tasks and explained his expectations from your analysis. Minutes of this meeting are available on the next page. Now, your job is to review and complete the allocated tasks as per this document. MIS771 - Descriptive Statistics and Visualisation Trimester 1, 2017 Page 5 of 11 Form 210-3 ANALYTICS7 Team Meeting ANALYTICS7, 727 Collins St, Docklands VIC 3008 Phone: (+61 3 212 66 000) [email protected] Reference AP-210 AusPaper Project Revised April 24, 2017 Level Expert Analysis Meeting Chair Hugo Barra Date 22 April 2017 Time 11:00 AM Location ANALYTICS7 L2.110 Topic AusPaper Research Project – Analytics Details Meeting Purpose: Specifying and Allocating Data Analytics Tasks Discussion items: • Variable(s) description. • Predicting customer satisfaction with AusPaper products. • Predicting the likelihood of clients developing strategic alliance with AusPaper. • Predicting AusPaper’s financial turn-over in the upcoming three-quarter. • Producing a technical report. Detailed Action Items Who: Graduate Intern What: 1. Providing an overall summary of two outcome (dependent) variables of interest: One variable captures the extent of satisfaction with previous purchases from AusPaper. The other one indicates whether a client perceives his/her firm would engage in strategic alliance or partnership with AusPaper. 2.1. Identifying 15 factors (from AusPaper_Data) that may influence customer satisfaction with AusPaper. An appropriate statistical technique could be used here to identify a list of predictors that could be included in the regression model. 2.2. Building and finalising a model (Model building process) to predict customer satisfaction with AusPaper. 2.3. Hugo has done a separate analysis and found that the depth and breadth of AusPaper ‘product line’ is a significant predictor of ‘customer satisfaction’. In line with his findings, prior research shows that the strength of this relationship may vary according to ‘customer location’. That is, customers from global markets have needs that are more diverse compared to those from a specific region such as ANZ. Thus, the relationship between ‘product line’ diversification and ‘customer MIS771 - Descriptive Statistics and Visualisation Trimester 1, 2017 Page 6 of 11 satisfaction’ should be more prominent for customers in global markets (i.e. outside ANZ region). Your task here is to test Hugo’s assumption by modelling an interaction effect between the above-mentioned independent variables and ‘customer satisfaction’. 3.1. Building and finalising a model (through a model building process) to predict the “likelihood of customers developing strategic alliance/partnership” with AusPaper.Hugo has already done an initial analysis for this task. Based on his analysis, Hugo has narrowed down the key predictors of “customers likelihood to build a strategic alliance/partnership” to the following: Product Quality, Product Line, Personnel Image, Price Flexibility, and Competitive Pricing Your job now is to continue his work by finalising a predictive model of key factors that influence the “likelihood of building a strategic alliance/partnership”.Hugo would like to gain a deeper understanding of customers’ likelihood for building strategic alliance/partnership with AusPaper. He is specifically interested in understanding the probability of having strategic alliance with AusPaper for customers who meet the following criteria: a) Feel neutral (i.e. score of 5 on the relevant scales) towards AusPapers’ image and its product line. b) Varying levels of perception towards product quality (i.e., scores from 1 to 10) and price flexibility (scores of 0, 5, and 10). Hugo believes that ‘price flexibility’ and ‘product quality’ would define AusPaper’s success in building strategic alliance with its customers. Therefore, it is important for AusPaper to know how flexible its sales representatives should be in negotiating prices on the one hand, and how much effort should be put in improving perceptions of product quality in order to increase the probability of building strategic alliance. Accordingly, your job is to visualise the predicted probability of building strategic alliance with AusPaper for customers with varying levels of ‘product quality’, and ‘product flexibility’ perceptions and fixed perception towards ‘product line’ diversity and personnel ‘image’. 4. Developing a time-series model to forecast AusPaper financial turnover in the next 3 quarters. It is your job to decide which time-series model is most appropriate in this scenario. 5. Produce a written report detailing ALL aspects of your analysis. Your report should be as detailed as possible and should describe ALL key outputs of your analysis. Next meeting Monday 15 May MIS771 - Descriptive Statistics and Visualisation Trimester 1, 2017 Page 7 of 11 Appendix: Explanatory Notes To accomplish allocated tasks, you need to examine and analyse the dataset (AusPaper.xlsx) thoroughly. Below are some guidelines to follow: Task 1 – Summarising Dependent Variables The purpose of this task is to analyse and explore key features of these two variables individually. At very least, you should thoroughly investigate relevant summary measures of for these two variables. Proper visualisations should be used to illustrate key features of these two variables. Your technical report should describe ALL key aspects of each variable. Reference: Module 1 – Topic 2 Task 2.1. – Identifying relevant factors for predicting customer satisfaction Analyse the relevant dependent variable against other variables included in the dataset. Your job is to decide which variables to include here. Use an appropriate technique to identify important relationships. The outcome of this task is a list of variables that should be included in the subsequent analysis. Your technical report should describe why some variables were selected while others were dropped from subsequent analyses. Reference: Module 2 – Topic 1 and 2 Task 2.2. – Model Building (Predicting Customer Satisfaction) You should follow model building process outlined in Module 2 – Topic 2. All steps of model building process should be included in your analysis. You can have as many Excel worksheets (tabs) as you require to clearly demonstrate different iterations of your predictive model (i.e., 2.2.a., 2.2.b., 2.2.c. etc.). Note that your final model should only include those variables that have predictive value. Your technical report should clearly explain why the model may have undergone several iterations. Also, you must provide detailed interpretation of ALL elements of the final model. Reference: Module 2 – Topic 2 MIS771 - Descriptive Statistics and Visualisation Trimester 1, 2017 Page 8 of 11 Task 2.3. – Interaction Effect To accomplish this task you need to develop a regression model using ONLY factors discussed in the ‘minutes of the meeting – Task 2.3.’. In other words, this section of analysis is separate from the regression model constructed in Task 2.2. Your technical report should clearly explain the role of each variable included in the model. A proper visualisation technique should be used. Make sure you interpret all relevant outputs in detail and provide managerial recommendations based on the results of your analysis. Reference: Module 2 – Topic 2 Task 3.1. – Model Building (Likelihood of Building Strategic Alliance/Partnership) You should start building the predictive model by including ONLY the variables listed in the ‘minutes of the meeting – Task 3.1.’. You are required to demonstrate all iterations of your predictive model. Note that your final model should only include those variables that have predictive value. Your technical report should clearly explain why the model may have undergone several iterations. A detailed interpretation of ALL elements of the final model must be provided. Reference: Module 2 – Topic 2 and 3 Task 3.2. – Visualising and Interpreting Predicted Probabilities Your technical report must include the predicted probability visualisation and be supplemented by practical recommendations to Hugo Barra (or AusPaper). These recommendations should answer the following question: “How change product quality (scores from 0 to 10) and price flexibility (scores of 0, 5, and 10) may affect the predicted probability of building strategic alliance with AusPaper for customers who have neutral feeling (fixed score of 5) towards personnel image and product line?” Reference: Module 2 – Topic 3 Tutorial MIS771 - Descriptive Statistics and Visualisation Trimester 1, 2017 Page 9 of 11 Task 4. – Forecasting Turnover AusPaper’s quarterly turnover from quarter one 2008 to quarter one 2017 are given in the AusPaper_Turnover worksheet. Your job is to develop a proper forecasting model to predict turnover for the next three quarter (i.e. Q2 to Q4 2017). In your technical report, you must explain the reason for selecting the forecasting method to predict future turnover. The report also must include a detailed interpretation of the final model. (e.g. a practical interpretation of the time-series model, choices about smoothing technique etc.). Reference: Module 2 – Topic 4 Task 5. – Technical Report Your technical report must be as comprehensive as possible. ALL aspects of your analysis and final outputs must be described/interpreted in detail. Remember, your audience (i.e., Hugo) is an expert in Analytics and he expects nothing but perfection from your report. Perfection means quality content (demonstrated attention to details) as well as an aesthetically appealing report. Note that you can use as many technical terms as you require. Your report should also include an introduction as well as a conclusion. Introduction begins by highlighting the main purpose(s) of analysis and concludes by explaining the structure of the report (i.e., subsequent sections). Conclusion should highlight the key findings of analyses and explain the main limitations. MIS771 - Descriptive Statistics and Visualisation Trimester 1, 2017 Page 10 of 11 Submission Guide The assignment consists of two parts: Analysis and Technical Report. You are required to submit both your written report (Word.docx document only) and analysis (Excel.xlsx file only). This assignment is equivalent of 2,500 words. Analysis (excel.xlsx) The analysis should be submitted in the appropriate worksheets in the Excel file. Each step in the model buildings should be included in a separate tab (e.g. 2.2.a., 2.2.b., …; and 3.2.a. 3.2.b., …). If you need more worksheets, then add them. Before submitting your analysis make sure it is logically organised and any incorrect or unnecessary output has been removed. Marks will be penalised for poor presentation or disorganised/incorrect results. Your worksheets should follow the order by which tasks are allocated in the minutes of meeting document. Note: Give the Excel file an appropriate name such as MIS771_A2_studentID.xlsx. Use a short file name while you are doing the analysis – once you complete your analysis rename the file to the format mentioned above. Technical Report (word.docx) Your technical report consists of four sections: Introduction, Main Body, Conclusion, and Appendices. The report should be no longer than 2,500 words. It could be shorter as long as all the aspects of the assignment tasks are addressed in detail. Use proper headings (i.e., 1., 2.1., 2.2., …) and titles in the main body of the report. Use sub-headings where necessary. Relevant tables, charts, or graphs MUST be included in the report as Appendices (not included in the word count). Make sure these outputs are visually appealing; have consistent formatting style and proper titles (title, axes titles etc.); and are numbered correctly. Where necessary, refer to these outputs in the main body of the report. Note: Name the report with an appropriate file name such as MIS771_A2_studentID.doc. MIS771 - Descriptive Statistics and Visualisation Trimester 1, 2017 Page 11 of 11 Sample Rubric Criteria Name Criteria Weight Not Attempted Needs Improvement Satisfactory Good Very Good Exemplary Analysis (45%) GLO1 GLO3 Task 1 5% Does NOT use any appropriate descriptive analysis tool. Use irrelevant or inappropriate descriptive analysis tool. Use appropriate descriptive analysis tool BUT there are errors in the analysis. Most relevant descriptive analysis tools are used BUT there are minor errors in the analysis. All relevant descriptive analysis tools are used with minor errors in the analysis. Skilful and comprehensive descriptive analysis of all relevant variables using variety of techniques. Task 2 15% Does NOT use any appropriate bivariate exploratory data analysis tool. Use irrelevant or inappropriate bivariate analysis tool. Use appropriate bivariate analysis tool to identify IVs, BUT there are errors in the analysis. Appropriate bivariate analysis tool is used, BUT NOT all relevant IVs are identified. All relevant IVs are identified using proper bivariate analysis technique, BUT minor issues noted. Skilful and comprehensive analysis of bivariate relationships is presented and all relevant IVs are identified. Either inappropriate predictive model is developed and/or analysis lacks All steps of modebuilding process missing. Relevant IVs are included in the predictive model, BUT some steps of model-building process missing. A predictive model is developed with All model-building steps included, BUT the final model is incorrect and/or there are many errors in the analysis. An appropriate predictive model is developed with All model-building steps presented BUT there are minor errors in the analysis. The final model includes those IVs that have predictive power with All steps in model-building process clearly presented. Model-building process is presented in logical/comprehensive manner AND the final model is correct. Interaction analysis is missing. Interaction analysis is incorrect. Analysis of interaction effects is presented BUT there are many errors. Interaction analysis is done correctly BUT wrong visualisation technique is used. Interaction analysis is presented accurately with proper visualisation technique BUT with minor errors. Masterful analysis of interaction effects supplemented by a correct visualisation. Task 3 15% Either inappropriate predictive model is developed and/or analysis lacks All steps of modebuilding process missing. Relevant IVs are included in the predictive model, BUT some steps of model-building process missing. A predictive model is developed with All model-building steps included, BUT the final model is incorrect and/or there are many errors in the analysis. An appropriate predictive model is developed with All model-building steps presented BUT there are minor errors in the analysis. The final model includes those IVs that have predictive power with All steps in model-building process clearly presented. Model-building process is presented in logical/comprehensive manner AND the final model is correct. Predicted probabilities are not calculated and/or a visualisation is missing. Not All Predicted probabilities are calculated and/or a visualisation is missing. All predicted probabilities are calculated and a visualisation is presented BUT there are many errors in the analysis. All predicted probabilities are calculated and a visualisation is presented BUT there are minor errors in the analysis. All predicted probabilities are calculated correctly and a proper visualisation is presented. A skilful and comprehensive analysis of predicted probabilities is presented along with a wellstructured visualisation. Task 4 10% Does not use any appropriate time-series techniques. Uses irrelevant or inappropriate techniques to analyse the time-series and/or there are many errors in the analysis. A relevant time-series model developed but there are many errors in the analysis. A relevant time-series model is developed and but there are minor errors in the analysis. Time-series model is developed correctly and relevant measure(s) for evaluating the model quality is presented. Time-series model developed correctly and presented in a clear and logical fashion including relevant visualisations. Interpretation GLO1 GLO5 - 45% Does not communicate any of the main findings of the analysis in an accurate or meaningful way. Interpretation and communication of findings is at a basic level or does not adequately explain the main findings of the analysis. Explains the main findings of the analysis accurately and enables reader to draw some reasonable conclusions. Provides an accurate description of the most - BUT NOT ALL - important features of the analysis, with appropriate conclusions. Provides very detailed and accurate descriptions of the most important features of the analysis. Provides an outstanding description and conclusion of All relevant analysis/visualisation outputs. Interpretation of results are novel and insightful. Technical Report GLO1 GLO5 - 10% The technical report is poorly structured and/or few sections missing with a poor use of technical language. The technical report is poorly structured. Only few analysis outputs are presented in appendix. Language is difficult to follow with many grammatical errors noted. The technical report is wellstructured with All required sections included. Most relevant analysis outputs are included in appendix. Communication is NOT clear throughout the report and grammatical errors noted. The technical report is wellstructured with All sections included. All relevant analysis outputs are included in appendix. Communication is clear with NO grammatical errors noted. The technical reports on par with a professional report. All relevant analysis outputs are presented in appendix in a logical order. Written communication is clear, easy to follow and has a structure. The technical report is masterfully structured. All relevant analysis outputs are included in appendix. Outputs are visually appealing, and follow a consistent formatting style. Language is truly professional and easy to follow OVERALL 100% (Equivalent of 35 Marks) 0-29% 30%-49% 50%-59% 60%-69% 70%-79% 80%-100% Overall Description Fail (n) Pass (P) Credit (C) Distinction (D) High Distinction (HD)