I currently have to determine the adequacy of resources, by reviewing the resources given to me.
DA 201 Introduction to Data Analytics Fall 2020 Lab 1 Analytics Requirements (Discovery Phase) at Goethe Industries Total Points available = 100 Background Goethe Industries was founded by Parsifal Goethe (pronounced gurter) in 1999. Goethe is an insurance company for large corporate concerns with customers nationwide.. They offer a range of standard low cost insurance policies. The three key concepts here are Customers, Portfolios and Policies. A portfolio is a collection of policies for the same customer. The company is marginally profitable but there is always room for improvement and they face competition from other industry leaders such as Heidegger Limited, Schopenhauer Amalgamated and Intangibles Incorporated. Customer churn is currently running at 25% per year. The company is seeking to both improve the value of customers and cut down on customer churn (the loss of customers to rivals) . They have a number of aims: · To develop a marketing campaign to help attract and retain customers · To develop a data warehouse to help marketing and customer support groups · They want to reduce customer churn by 20%. · They want to know why customers are "churning" · They want to know whether the effort/cost to retain customers is worth it. Resources available to the company: A traditional Relational Database holding details of customers and their policies and portfolios. Detailed policy and portfolio data ( portfolio creation, portfolio closing, consolidation, transfers, policy details) goes back 5 years, events older than 5 years are summarized in customer records as yearly summary records. Portfolio and policy data include opening and closing dates, and holder details. An Analytics Sandbox: An area separate from production systems where data can be analyzed with no risk to live data – currently empty! You will have access to R (cos it is free) and SAS and MATLAB and MySQL and Excel. A small team of Business Intelligence Analysts (3 problem domain experts) CEO (Sponsor) Functional Unit Leaders (VPs of Sales, Marketing, HR, Finance, Customer Support) Financial Analysts The IT Division (Project Manager, DBA(veteran) and Data Engineer(trainee)) You – an aspiring Data Scientist Refer to the notes about what types of role are typically involved in Data Analytics Projects Your task 1.Identify the Business Problem that can be solved by a Data Analytics Project From the narrative above what is the business problem that you are trying to help solve by developing a Data Analytics Project. An Analytics Project will not solve a business problem but it (hopefully) will provide sufficient insights so that actions can be taken to solve the problem. So for instance if your company is spending $1M a year in warehouse costs for a slow moving item then knowing this may lead to a new JIT stock policy where little or no stock is held thus drastically cutting warehousing costs. 2. Formulate one or more initial hypotheses An initial hypothesis for our purposes is a starting point from which we can plan to do stuff. Our thinking will very likely change as we gather data, analyze it and see the implications of our analyses … but we have to start somewhere. Think of it as a best guess. A hypothesis is something that can be tested and will be supported or not by the results of our analyses. So for instance if the business problem is "how do we maximize profits from our customers" your initial hypothesis (IH) might be "Segmenting the customer base by standard classifications of type will improve our ability to provide better tailored products" or (IH) "dividing the customer base into different groups can improve targeting of discounts and incentives". This gives you some testable hypotheses and helps determine the kind of data you need. 3. Determine adequacy of resources From the problem description above and based on your initial hypotheses do you think you have the resources you will need to perform an Analytics project. Resources include Data, Technology Resources, Project team Skills. So do you have the right data, if not what additional data would be necessary to do a meaningful project bearing in mind your initial hypotheses – how might you go about collecting this data? Do you have the right technology – this is tricky as many of you may have limited experience here. Some strategic research on what the technology listed above can do may be valuable here. Do you have the right people and do they have the right skills? What skills would you expect from the key players in the project. If you fear they do not have the right skills what can you do about it? The Discovery Phase Plan: 30 Points Page length – 2 to 5 pages excluding title page 1. Report Title: Report Title page including Group Name, authors and date. 2. The Business Problem 3. The initial Hypotheses 4. Resource Evaluation 5. Bibliography and citations If you found it useful to do research elsewhere you need to document your sources. The bibliography should include all materials you have used such as slides from the in-class sessions if you referred to them and any external sources. Make sure you cite them correctly within the document (inline) as well as presenting a listing in the bibliography. Cutting and pasting from the web or other electronic sources is not permitted, the report is to be wholly in your own words. If your report uses the ideas of others you will represent them in your own words and properly cite them. You will use inline citations for example "Brown & Duguid (2001) argue that communities of practice present a special case of networks of practice..". Each inline citation must match an entry in the bibliography. As for citation standards you may use MLA or APA or another style that you prefer but it must be a recognized style and it must be consistent. If you are presenting the exact or near exact words of another author they must be very short, you must italicize them, enclose them in quotation marks, use a smaller font, indent them from left and right and make sure the source is properly cited, for instance: "The role of the teacher, in any context, involves direct instruction that makes use of the subject matter and pedagogical expertise of the teacher". (Anderson, Rourke et al. 2001) Presenting the words/ideas of someone else without suitable attribution is plagiarism and will be treated as a breach of academic honesty. Simply taking the ideas of someone else and rewriting them in your own words does not mean you are not plagiarizing. If you use the ideas of someone else you must attribute those ideas correctly both in the text inline and in the Bibliography – it is not sufficient to simply rewrite them you must explicitly say whose ideas they are and where they came from Use direct quotations very sparingly and only when absolutely necessary. In this report there should be no need for direct quotations. You are free to use diagrams, images and tables from elsewhere as long as they are directly relevant and as long as they are properly cited. In short I need to know with absolute certainty whether what you are presenting is your own creative process or that of others. Deadlines: Reports must be submitted via Blackboard on Friday 25th September by 11:30pm.