Data science applications and usecases
2 likes4,919 views
The document provides an overview of data science applications and use cases. It defines data science as using computer science, statistics, machine learning and other techniques to analyze data and create data products to help businesses make better decisions. It discusses big data challenges, the differences between data science and software engineering, and key areas of data science competence including data analytics, engineering, domain expertise and data management. Finally, it outlines several common data science applications and use cases such as recommender systems, credit scoring, dynamic pricing, customer churn analysis and fraud detection with examples of how each works and real world cases.
Data science applications and usecases
- 1. Hello… Welcome To the Talk on Data Science Applications and Use cases
- 2. Agenda… • What is Data Science? • Big Data Challenges • Data Science vs Software Engineering • Data Science Applications & Use cases • Conclusion
- 3. What is Data Science? Data Science is the science which uses computer science, statistics and machine learning, visualization and human-computer interactions to collect, clean, integrate, analyze, visualize, interact with data to create data products. “Using data to make better decisions, optimize processes and improve products and services.” “What distinguishes data science itself from the tools and techniques is the central goal of deploying effective decision-making models to a production environment. “ – John Mount & Nina Zumel, Practical Data Science with R
- 4. Big Data Challenges • Dealing with Data Growth • Generating insights in a timely manner • Integrating disparate data sources • Validating Data • Securing Bigdata • Organizational resistance
- 6. ‘Data science’ is “Data-Driven Decision” making, to help the business to make good choices, whereas software engineering is the methodology for software product development without any confusions about the requirements. Data Science vs Software Engineering
- 7. Data Science Competence Groups - Research Data Science Competence includes 5 areas/groups • Data Analytics • Data Science Engineering • Domain Expertise • Data Management • Scientific Methods (or Business Process Management) Scientific Methods • Design Experiment • Collect Data • Analyse Data • Identify Patterns • Hypothesise Explanation • Test Hypothesis Business Operations • Operations Strategy • Plan • Design & Deploy • Monitor & Control • Improve & Re-design
- 8. Data Science Competence includes 5 areas/groups • Data Analytics • Data Science Engineering • Domain Expertise • Data Management • Scientific Methods (or Business Process Management) Scientific Methods • Design Experiment • Collect Data • Analyse Data • Identify Patterns • Hypothesise Explanation • Test Hypothesis Business Process Operations/Stages • Design • Model/Plan • Deploy & Execute • Monitor & Control • Optimise & Re-design Data Science Competences Groups – Business Design Modelling Execution Monitoring Optimisation RESEARCH DATA ANALYTICS ALGORITHMSANALYTIC SYSTEMS ENGINEERING COMPETENCES DOMAIN EXPERTISE DATA SCIENCE Data Management Scientific Methods Business Process Management
- 9. Data Science Applications & Use cases • RECOMMENDER SYSTEMS • CREDIT SCORING • DYNAMIC PRICING • CUSTOMER CHURN • FRAUD DETECTION
- 10. RECOMMENDER SYSTEMS WHAT IS A RECOMMENDER SYSTEM? A model that filters information to present users with a curated subset of options they’re likely to find appealing HOW DOES IT WORK? Generally via a collaborative approach (considering user’s previous behavior) or content-based approach (based on discrete assigned characteristics) WHAT IS A REAL USE CASE? Tendril uses recommendation models to match eligible customers with new or existing energy products
- 11. CREDIT SCORING WHAT IS CREDIT SCORING? A model that determines an applicant’s creditworthiness for a mortgage, loan or credit card HOW DOES IT WORK? A set of decision management rules evaluates how likely an applicant is to repay debts WHAT IS A REAL USE CASE? Ferratum Bank uses machine learning models to reach prospective customers that may have been overlooked by traditional banking institutions
- 12. DYNAMIC PRICING WHAT IS DYNAMIC PRICING? Modeling price as a function of supply, demand, competitor pricing and exogenous factors HOW DOES IT WORK? Generalized linear models and classification trees are popular techniques for estimating the “right” price to maximize expected revenue. WHAT IS A REAL USE CASE? Turo uses dynamic pricing models to suggest prices to the people who list and rent out cars
- 13. CUSTOMER CHURN WHAT IS CUSTOMER CHURN? Predicting which customers are going to abandon a product or service HOW DOES IT WORK? Data scientists may consider using support vector machines, random forest or k-nearest-neighbors algorithms WHAT IS A REAL USE CASE? EAB combines data from transcripts, standardized test scores, demographics and more to identify students at risk of not graduating.
- 14. FRAUD DETECTION WHAT IS FRAUD DETECTION? Detecting and preventing fraudulent financial transactions from being processed HOW DOES IT WORK? Fraud detection is a binary classification problem: “is this transaction legitimate or not?” WHAT IS A REAL USE CASE? Via SMS Group uses a combination of complex data lookups and decision algorithms written in R and implemented in PHP to assess whether a loan applicant is fraudulent
- 15. Works Cited • https://www.yhat.com/whitepapers/data-science-in-practice • http://wikibon.org/blog/role-of-the-data-scientist/ • https://www.cyfronet.krakow.pl/cgw16/presentations/S8_02_present ation-Edison-CGW-26-10-2016.pdf
- 16. Thank You Sreenatha Reddy K R [email protected] https://in.linkedin.com/in/sreenathaa
Editor's Notes
- #14: Churn rate describes the rate at which customers abandon a product or service. Understanding customers’ likelihood to churn is particularly important for subscription-based models, everything ranging from traditional cable or gym memberships to recently popularized monthly subscription boxes.