Fundamentals of Data Science PDF
Document Details
Uploaded by PlayfulTragedy
Rome Business School
2024
Tags
Summary
This document is lecture notes on Fundamentals of Data Science from ROME BUSINESS SCHOOL. The lecture is on data science, data analytics, and business management. The lecture notes are from October 2024.
Full Transcript
Better Managers for a Better World Fundamentals of Data Science Module: Data Analytics Master: Blended OL: Finance, Supply, Sustain, Pharma OL Date of lecture: Oct 2024 romebusinessschool.com Agenda 1. Introduction to...
Better Managers for a Better World Fundamentals of Data Science Module: Data Analytics Master: Blended OL: Finance, Supply, Sustain, Pharma OL Date of lecture: Oct 2024 romebusinessschool.com Agenda 1. Introduction to Data Science 2. Part 1 Data-driven companies Data Culture Data Strategy and Data Governance 3. Part 2 Data Science organization and methodologies Data Privacy, Security and Ethics Advanced Analytics Data Visualization and effective communication 4. Business case 5. Q&A romebusinessschool.com Better Managers for a Better World Disclaimer All product and company names are trademarks or registered® trademarks of their respective holders. The use of registered names, logos, brands, etc. does not imply any affiliation with or endorsement by them. romebusinessschool.com Better Managers for a Better World Introduction to Data Science (recap) romebusinessschool.com Better Managers for a Better World What is Data Science? Study of data to extract meaningful insights for business https://towardsdatascience.com/introduction-to-statistics-e9d72d818745 romebusinessschool.com Better Managers for a Better World 5 Data is the new oil! Questa foto di Autore sconosciuto è concesso in licenza da CC BY romebusinessschool.com Better Managers for a Better World 6 Big Data Structured Data (20%) Unstructured Data (80%) https://statanalytica.com/blog/4-vs-of-of-big-data/ romebusinessschool.com Better Managers for a Better World 7 2023 Top Trends in Data and Analytics 1. Thinking Like a Business Focus on adopting a proactive approach to delivering value 2. From Platforms to Ecosystems Ensure a consistent and holistic view of both the technical and the organizational contexts 3. Don’t Forget the Humans Avoid to become too data-centric or technology enamored, and lost touch with the employees https://www.gartner.com/doc/reprints?id=1-2D5XJT8I&ct=230407&st=sb romebusinessschool.com Better Managers for a Better World 9 2023 Top Trends in Data and Analytics Data and analytics leaders must: 1. act more like an internal consulting company with its own P&L than a business support function that represents a cost center to the rest of the business 2. plan their D&A strategy in the context of ecosystem thinking where each element impacts and is impacted by the whole 3. plan on engaging with stakeholders across the organization to understand the best approach to drive D&A adoption, aligned with human psychology and values https://www.gartner.com/doc/reprints?id=1-2D5XJT8I&ct=230407&st=sb romebusinessschool.com Better Managers for a Better World 10 Part 1 Data-driven companies Data Culture Data Strategy and Data Governance romebusinessschool.com Better Managers for a Better World The value of the Data Information romebusinessschool.com Better Managers for a Better World 12 The only one thing worse than a Pie Chart is … lots of them (E. Tufte - Father of Infographic) https://it.wikipedia.org/wiki/Edward_Tufte romebusinessschool.com Better Managers for a Better World 13 DIKW pyramid + Understanding = Wisdom: stop + Meaning = Knowledge: direction + Context = Information: traffic light Raw Data: red romebusinessschool.com Better Managers for a Better World 14 Data, Information & Insights Raw and unprocessed facts Data Last month, the marketing team received 2,000 leads Processed data (What is happening) Information Last month, the leads grew by 20% over the previous month Information + Knowledge (Why is happening) Insights Growth in leads come from the website live chat recently deployed https://treehousetechgroup.com/understanding-the-difference-between-data-information-and-business-insights romebusinessschool.com Better Managers for a Better World 15 What is a Data-driven company? A company that: relies on data and information for decision making, from daily basis operational to long-term strategic decisions spread an internal culture that recognizes the value of data and information to face and overcome the business challenges romebusinessschool.com Better Managers for a Better World 16 Why become a Data-driven company? + Productivity: increased efficiency + Revenue: less costs, greater incomes + Competitive advantage: Customer Experience & Customer Retention 81% of managers agree that data are at the heart of all decision-making https://assets.ey.com/content/dam/ey-sites/ey-com/en_gl/topics/digital/ey-global-becoming-an-analytics-driven-organization.pdf romebusinessschool.com Better Managers for a Better World 17 We live in a world V U C A Volatile Uncertain Complex Ambiguous or B A N I Brittle Anxious Non Linear Incomprehensible romebusinessschool.com Better Managers for a Better World 18 In a world strategic and operational decisions need to be based on data, rather than intuition, opinions or experience romebusinessschool.com Better Managers for a Better World 19 “Trust me...... I have a lot of experience... I have already faced this situation, many times... I know how things are going” W.E. Deming (1900-1993): “In God we trust. All others must bring data.” https://it.wikipedia.org/wiki/William_Edwards_Deming romebusinessschool.com Better Managers for a Better World 20 Beware of HiPPO - Highest Paid Person’s Opinion romebusinessschool.com Better Managers for a Better World 21 Not only HiPPOs in our company https://www.werkvuur.nl romebusinessschool.com Better Managers for a Better World 22 Data-driven Strategy Processes People Organization Technology romebusinessschool.com Better Managers for a Better World 23 romebusinessschool.com Better Managers for a Better World https://onlinedegrees.unr.edu/blog/data-driven-culture 24 How to create a Data Culture You can’t import Data Culture You can’t impose Data Culture 1. The goal is to make better decisions 5. Change Agents 2. Commitment from CEO and board 6. Build Ecosystems 3. Data Democratization 7. Integrate the right talents 4. Developed on risk management https://www.mckinsey.com/~/media/McKinsey/Business%20Functions/McKinsey%20Analytics/Our%20Insights/Why%20data%20culture%20matters/Why-data-culture-matters.ashx romebusinessschool.com Better Managers for a Better World 25 How to create a Data Culture Data as the universal basis for decision making 7. Make proofs of concept simple and robust, not fancy and brittle 1. Data-driven culture starts at the top 8. Training offered just in time 2. Choose metrics with care 9. Use analytics to help employees, 3. Don’t pigeonhole your data not just customers scientists 10. Trade flexibility for consistency 4. Fix basic data-access issues quickly (in the short term) 5. Quantify uncertainty 11. Explain analytical choices https://hbr.org/2020/02/10-steps-to-creating-a-data-driven-culture romebusinessschool.com Better Managers for a Better World 26 How to create a Data Culture Connect data to organizational culture Develop data professionals who speak the language of business 1. Articulate the relationship between data and business operations 2. Correct the misperception that data is just for techies 3. Show how data solves problems at all levels of the organization https://mitsloan.mit.edu/ideas-made-to-matter/3-ways-to-build-a-data-driven-culture-your-organization romebusinessschool.com Better Managers for a Better World 27 How to create a Data Culture Data as an essential part of business processes Data culture test: a data lost causes … https://www.forbes.com/sites/brentdykes/2019/03/28/the-four-key-pillars-to-fostering-a-data-driven-culture romebusinessschool.com Better Managers for a Better World 28 How to create a Data Culture Executive sponsorship Data Literacy Single version of truth Strategy alignment Quick Wins Data Storytelling Self-service model Data Governance https://www.forbes.com/sites/brentdykes/2019/03/28/the-four-key-pillars-to-fostering-a-data-driven-culture romebusinessschool.com Better Managers for a Better World 29 Data-driven Strategy Data Strategy Strategy for the usage and the sharing of data, in order to achieve goals consistent with the Business Strategy Data Governance Planning, implementation and monitoring rules on data management (assets) Data Management Lifecycle management and data enhancement FAIR principles: Findable, Accessible, Interoperable, Reusable romebusinessschool.com Better Managers for a Better World 30 Data Strategy Strategy for using and sharing data, in order to achieve goals consistent with the Business Strategy How can we use data for generating value for the Business? What are our critical (data) assets? What is the existing data ecosystem? How do we govern data? romebusinessschool.com Better Managers for a Better World 31 Data Strategy Strategy for using and sharing data, in order to achieve goals consistent with the Business Strategy Identify Business objectives and define related Data Strategy objectives Conduct an assessment of the AS IS status of policies, procedures, processes, data sources, technology infrastructure and tools, and skills Define a Roadmap to target the set objectives, including incrementally and iteratively Identify and implement necessary Change Management actions to support changes on organization, culture, technology tools, and business processes romebusinessschool.com Better Managers for a Better World 32 There is nothing quite so useless, as doing with great efficiency something that should not be done at all (P. Drucker - Management consultant and educator) https://en.wikipedia.org/wiki/Peter_Drucker romebusinessschool.com Better Managers for a Better World 33 Data Governance Planning, implementation and monitoring rules on data (asset) management Who is the Data Owner? Who is authorized to access the data? Which security measures are protecting the data? Which are the reliable data sources used? romebusinessschool.com Better Managers for a Better World 34 Data Governance Planning, implementation and monitoring rules on data (asset) management Data Policy - rules for organizing, managing and sharing data Data Quality - levels and metrics of data quality Risk Management - management of risks and impacts on business Regulatory Compliance - compliance with laws, regulations, etc. Business Policies - consistency and compliance with business policies Business Process Management - integration with all business processes romebusinessschool.com Better Managers for a Better World 35 romebusinessschool.com Better Managers for a Better World 36 Data Management Lifecycle management and data enhancement Which methods and technologies are used to acquire/store data? Which procedures and tools are used to ensure data quality? How is it ensured the integration of different systems and data sources? Which measures are taken to ensure data accessibility and reuse (Secondary Data Analysis)? romebusinessschool.com Better Managers for a Better World 37 Data Management Lifecycle management and data enhancement, through the Data Management Plan Enables planning, documentation and monitoring of data management Defines roles and responsibilities throughout the data lifecycle Contains information on how data are acquired, described, processed, managed, shared, and preserved over time Outlines principles and collects guidance on metadata standards used, how data are protected from accidental loss, whether there are restrictions on access, sharing, exporting https://libraries.mit.edu/data-management/plan/write romebusinessschool.com Better Managers for a Better World 38 Data maturity Data Driven Data Culture Data Proficient Decisions and strategies built on Real-time Dashboard data analysis Data Aware Centralized Analytics Reports Business Intelligence KPI The past The present The future romebusinessschool.com Better Managers for a Better World 39 7 out of 10 companies fail to become data-driven Main reasons of failure Viewing data-driven transformation as something that impacts only the IT department Focusing on the data at hand rather than on the strategic and business objectives to be achieved https://hbr.org/2019/02/companies-are-failing-in-their-efforts-to-become-data-driven romebusinessschool.com Better Managers for a Better World 40 Why becoming a Data-Driven company is so hard The biggest challenge is not the technology but the cultural change People and organizations need to adapt to change Think different: different mindset + critical thinking, human judgement, creative innovation Fail fast, learn faster: failure is the foundation of innovation Focus on the long-term: becoming data-driven is a process, success is achieved iteratively https://hbr.org/2022/02/why-becoming-a-data-driven-organization-is-so-hard romebusinessschool.com Better Managers for a Better World 41 Part 2 Data Science organization and methodologies Data Privacy, Security and Ethics Advanced Analytics Data Visualization and effective communication romebusinessschool.com Better Managers for a Better World Data-driven Strategy Processes People Organization Technology romebusinessschool.com Better Managers for a Better World 43 Data-driven Organization IT, or not IT: that is the question! CDO (Chief Data Officer) CEO Manage and develop data as a strategic business asset CISO Maximize the value to the business that can be extracted from data CIO CDO CDO (Data) (Digital) Define and implement data strategy and data governance Manage data security and compliance romebusinessschool.com Better Managers for a Better World 44 Eliminate silos Eliminate data silos Eliminate organizational silos romebusinessschool.com Better Managers for a Better World 45 Data Scientist Team 100% 90% 80% 70% 60% 50% 40% 30% 20% 10% 0% Valeria Anna Paolo Luca Giovanna Business Programming Programmazione Statistics Statistica Visualization Visualizzazione romebusinessschool.com Better Managers for a Better World 46 Data Science Processes - OSEMN Framework Project Lifecycle https://towardsdatascience.com/5-steps-of-a-data-science-project-lifecycle-26c50372b492 romebusinessschool.com Better Managers for a Better World 47 You can’t improve what you don’t manage measure https://towardsdatascience.com/5-steps-of-a-data-science-project-lifecycle-26c50372b492 romebusinessschool.com Better Managers for a Better World 48 Process Mining https://towardsdatascience.com/5-steps-of-a-data-science-project-lifecycle-26c50372b492 https://laredoute.io/blog/process-mining-101-why-should-we-care https://docs.appian.com/suite/help/23.2/pm-5.1/get_started/getting-started.html romebusinessschool.com Better Managers for a Better World 49 Data Security, Data Protection, Data Ethics Data Security Confidentiality, Integrity, Availability (Personal) Data Protection - Privacy Right to control personal data and protect it from abuses Data Ethics Avoid to adversely impact on people and society in data-related practices romebusinessschool.com Better Managers for a Better World 51 Data Security Implement redundant security measures Keep offline backup copies, or on a separate, unconnected IT infrastructure Classify data, information, documents, etc. Adopt specific protection solutions for storing and exchanging the most critical contents (i.e. passwords, encryption, restricted e-mail, protected PDFs, secure file sharing, Information Rights Management - IRM) romebusinessschool.com Better Managers for a Better World 52 Data Protection GDPR - EU General Data Protection Regulation 2016/679DPO DPO - Data Protection Officer Responsible for Data Protection Technical and Organizational Measures Privacy by Design - Privacy by Default romebusinessschool.com Better Managers for a Better World 53 Data Ethics ODI - Open Data Institute Data Ethics: assesses practices related to data that may have a negative impact on people and society (direct or indirect), at the level of its collection, sharing and use What is the main purpose of using data in this project? Data Ethics Canvas: tool to help identify and manage ethical issues, at the outset and Who might be adversely affected by this project? throughout a project using data https://theodi.org/wp-content/uploads/2019/07/ODI-Data-Ethics-Canvas-2019-05.pdf romebusinessschool.com Better Managers for a Better World 54 Data monetization - Devaluation of (raw) data By 2025, 75% of the world’s population will have their personal information covered by privacy regulations By 2025, 80% of marketers are expected to abandon personalization efforts, as consumers see such advertising as invasive or unhelpful https://towardsdatascience.com/5-steps-of-a-data-science-project-lifecycle-26c50372b492 https://www.dubaifuture.ae/reports/10-megatrends-shaping-our-future-in-2023 romebusinessschool.com Better Managers for a Better World 55 From Data to Knowledge romebusinessschool.com Better Managers for a Better World 57 From Data to Knowledge romebusinessschool.com Better Managers for a Better World 58 From Data to Knowledge romebusinessschool.com Better Managers for a Better World 59 From Data to Knowledge romebusinessschool.com Better Managers for a Better World 60 From Data to Knowledge romebusinessschool.com Better Managers for a Better World 61 From Data to Knowledge, to Wisdom https://www.evalueserve.com/blog/making-the-leap-from-insights-to-wisdom-a-collaborative-approach romebusinessschool.com Better Managers for a Better World 62 Data-Driven Decision Making (DDDM) Process Analyze Identify data business needs Extract valuable Acquire information data Identify Extract business valuable needs information Make Make decision decision https://towardsdatascience.com/5-steps-of-a-data-science-project-lifecycle-26c50372b492 romebusinessschool.com Better Managers for a Better World 63 Analytics https://medium.com/co-learning-lounge/types-of-data-analytics-descriptive-diagnostic-predictive-prescriptive-922654ce8f8f romebusinessschool.com Better Managers for a Better World 64 https://www.gartner.com/en/newsroom/press-releases/2014-10-21-gartner-says-advanced-analytics-is-a-top-business-priority romebusinessschool.com Better Managers for a Better World 65 To get the right answers ask the right questions (E. Hodnett - The art of problem solving) https://openlibrary.org/works/OL4968689W/The_art_of_problem_solving romebusinessschool.com Better Managers for a Better World 66 Data Visualization (Data Viz) Graphs Reports Business Intelligence Advanced Analytics romebusinessschool.com Better Managers for a Better World 67 How to effectively visualize information https://ducen.medium.com/how-to-give-your-web-analytics-a-boost-with-heat-maps-and-data-visualization-44f8419d99b8 romebusinessschool.com Better Managers for a Better World 68 https://tdwi.org/articles/2020/10/06/bi-all-data-story-visualization-decision-tree.aspx romebusinessschool.com Better Managers for a Better World 69 REMEMBER The only one thing worse than a Pie Chart is … lots of them (E. Tufte - Father of Infographic) https://it.wikipedia.org/wiki/Edward_Tufte romebusinessschool.com Better Managers for a Better World 70 A lot of Pie Charts romebusinessschool.com Better Managers for a Better World 71 A lot of Pie Charts https://www.tableau.com/blog/5-unusual-alternatives-pie-charts romebusinessschool.com Better Managers for a Better World 72 Visualize and interpret data Technical skills Domain knowledge Effective communication https://agencyanalytics.com/blog/data-storytelling romebusinessschool.com Better Managers for a Better World 73 It is easier to generate a lot of Reports that are worth very little, rather than generate few Reports that are woth a lot romebusinessschool.com Better Managers for a Better World 74 REMEMBER -=+ Less is more!!! romebusinessschool.com Better Managers for a Better World 75 https://piktochart.com/templates/infographics/2218-effective-communication-presentation/ Effective Communication https://www.sandler.com/blog/increase-your-communications-effectiveness-93/ romebusinessschool.com Better Managers for a Better World 76 Can we trust in Data Algorithms Automated Decision-Making (ADM) systems Artificial Intelligence ??? romebusinessschool.com Better Managers for a Better World 78 https://terrapintech.com/three-ways-data-centralization-will-help-establish-trust-in-data romebusinessschool.com Better Managers for a Better World 79 https://terrapintech.com/three-ways-data-centralization-will-help-establish-trust-in-data romebusinessschool.com Better Managers for a Better World 80 “In God we trust. All others must bring data.” (W.E. Deming) People don’t trust data 75% of Executives don’t trust their data People don’t understand data 32% of Executives are not able to generate value from data https://www.rtinsights.com/executives-dont-trust-data/ https://www.forbes.com/sites/forbestechcouncil/2023/02/10/the-problems-with-data-literacy/ romebusinessschool.com Better Managers for a Better World 81 Data-as-a-Product (DaaP) Data as a “shelf product” Higher utilization of “trusted data” Easier analysis by “consumers” Increase organization's ability to rapidly extract intelligence and insights from their data assets, in a low-friction manner https://phiona.com/blog/what-is-data-as-a-product https://www.forbes.com/sites/forbesbusinesscouncil/2022/09/21/what-is-a-data-product-and-what-are-the-key-characteristics romebusinessschool.com Better Managers for a Better World 83 Torture numbers, and they'll confess to anything (G. Easterbrook – Writer and Journalist) romebusinessschool.com Better Managers for a Better World 84 Business case romebusinessschool.com Better Managers for a Better World Data-driven Strategy for Retail Home ware retailer 30 stores all over EU Annual turnover of 200 millions of € Available data on customers, products, inventories, sales, operations, etc. romebusinessschool.com Better Managers for a Better World 86 Data-driven Strategy for Retail Challenge Implement an effective decision-making process, based on customers’ behaviors and product performance data, to develop a data-driven strategy Working in teams, please define: 1. at least 5 questions (Business needs) the DDDM process is expected to answer 2. the main steps to set-up and implement an effective DDDM process (from data acquisition to data elaboration and visualization) 3. at least 3 outputs (KPIs, Reports, Graphs, etc.) related to the Business needs, needed to be evaluated for making effective decisions romebusinessschool.com Better Managers for a Better World 87 Questions & Answers romebusinessschool.com Better Managers for a Better World In the next class 1. Business case (Class discussion) 2. Automated decision-making and Artificial Intelligence 3. Data-driven company success cases romebusinessschool.com Better Managers for a Better World 89 You can have the best technology, you can have the best business model, but if the storytelling isn’t amazing, it won’t matter: nobody will watch. (J. Bezos – Founder of Amazon) romebusinessschool.com Better Managers for a Better World 90 No part of this video or any of its contents may be reproduced, copied, modified of adapted, without the prior written consent of the author, unless otherwise indicated for stand-alone materials. Copyright Rome Business School All rights reserved romebusinessschool.com Better Managers for a Better World Better Managers for a Better World Thank you Via Giuseppe Montanelli, 5 00195, Roma RM romebusinessschool.com