The Data Science Handbook-I

Question 1

What are six steps in the business approach to analytics?

Answer 1

1. Understand where and how to leverage big data
2. Integrate analytics into everyday operation
3. Structure your organisation to drive analytics insights
4. Optimize processes, uncover opportunities, and stand out fom the rest
5. Help stakeholders to “think like a data scientist”
6. Understand appropriate business application of different analytics techniques

Question 2

Name the five phases of the Big Data Model Maturity Index.

Answer 2

1. Business Monitoring
2. Business Insights
3. Business Optimization
4. Data Monetization
5. Business Metamorphosis

Question 3

Phase 1 of the Big Data Business Model Maturity Index.

What is Business Monitoring?

Answer 3

Monitor key business processes and report on business performance using data warehousing techniques.

Question 4

Phase 2 of the Big Data Business Maturity Index.

What is Business Insights?

Answer 4

Pool all detailed operational and transactional data with internal unstructured and external (third-party, publicly available) data; integrate with advanced analytics to uncover customer, product, and operational insights buried in the data.

Question 5

Phase 3 of the Big Data Business Model Maturity Index.

What is Business Optimization?

Answer 5

Deliver actionable recommendations and scores to front-end employees to optimize customer engagement.

Deliver actionable recommendations to end customers based on their product and usage preferences, propensities, and tendencies.

Stage where organisations develop the predictive analytics and the prescriptive analytics necessary to optimize the targeted key business processes.

Question 6

Phase 4 of the Big Data Business Model Maturity Index.

What is Data Monetization?

Answer 6

Monetize the customer, product, and operational insights coming out of the optimization process to create new services and products, capture new markets and audiences, and create “smart” products and services.

This is the phase where organisations leverage the insights gathered from the Business Insights phase and Business Optimization phase to create new revenue opportunities.

Question 7

Phase 5 of the Big Data Business Model Maturity Index.

What is Business Metamorphosis?

Answer 7

Reconsititute customer, product, and operational insights to metamorphose the very fabric of an organization’s business model, including processes, people, compensation, promotions, products/ services, target markets, and partnerships.

Question 8

There are some interesting lessons that organizations will discover as they progress through the phases of the Big Data Business Model Maturity Index. Understanding these lessons ahead of time should help prepare organizations for their big data journey.

Which three lessons?

Answer 8

Lesson one. Focus initial big data efforts internally.
Internal process optimization starts by seeking to leverage BI and data warehouse (phase 1 to 3)

Lesson two. Leverage insights to create new monetization opportunities.
The opportunity to leverage the insights to create new revenue or monetization opportunities (phase 4 to 5).

Lesson three. Preparing for organizational transformation.
Organizational and cultural transformation.

Question 9

Lesson three. Preparing for organizational transformation.

To fully exploit the big data opportunity, subtle organizational and cultural changes will be necessary for the organization to advance along the maturity index. If organizations are serious about integrating data and analytics into their business models, then three organizational or cultural changes will need to take place.

Which three?

Answer 9

1. Treat data as an asset.
   Organizations must develop an insatiable appetitefor more and more data - even if they are unclear as to how they will use the data.
2. Legally protect your analytics intellectual property.
   Put formal processes in place to protect analytics intellectual property.
3. Get comfortable using data to guide decisions.
   Move from HIPPO to business decisions based on what data and analytics tell them.

Question 10

Define “corporate mission”.

Answer 10

Why the organization exists; defines what an organization is and the organization’s reason for being.

Question 11

Define “business strategy”.

Answer 11

How the organization is going to achieve its mission over the next two to three years.

Question 12

Define “strategic business initiatives”.

Answer 12

What the organization plans to do to achieve its business strategy over the next 9 to 12 months;
usually includes business objectives, financial targets, metrics, and time frames.

Question 13

Define “business entities”.

Answer 13

The physical objects or entities (e.g., customers, patients, students, doctors, wind turbines, trucks) around which the business initiative will try to understand, predict, and influence behaviours and performance (sometimes referred to as the “strategic nouns” of the business).

Question 14

Define “business stakeholders”.

Answer 14

Those business functions (sales, marketing, finance, store operations, logistics, and so on) that impact or are impacted by the strategic business initiative.

Question 15

Define “business decisions”.

Answer 15

The decisions that business stakeholders need to make in support of the strategic business initiative.

Question 16

Define “big data use cases”.

Answer 16

The analytic use cases (decisions and corresponding actions) that support the strategic business initiative.

Question 17

Define “data”.

Answer 17

The structured and unstructured data sources, both internal and external of the organisation, that will be indentified throughout the big data strategy document process.

Question 18

The big data strategy document is composed of which five sections?

Answer 18

1. Business strategy
2. Key business initiatives
3. Key business entities
4. Key decisions
5. Financial drivers (use cases)

Question 19

What does S.A.M. mean?

Answer 19

• Strategic - strategic to what the business is trying to accomplish
• Actionable - can act on
• Material - benefit is greater than the costs

Question 20

Why is the Business Insights phase the most difficult stage of the Big Data Business Model Maturity Index?

Answer 20

Because it requires organisations to “think differently” about how they want to approach data and analytics.

The rules, techniques, and approaches that worked in the Business Intelligence and data warehouse worlds do not necessary apply to the world of big data.

Also, much of the big data financial payback or Return on Investment (ROI) is not realized until the organisation reaches the Business Optimization phase.

Question 21

In which phase of the Big Data Business Model Maturity Index are the predictive and prescriptive analytics developed?

Answer 21

In the Business Optimization phase.

Question 22

Which four things are developed in the Business Optimization phase?

Answer 22

1. Create the prescriptive and predictive analytics to optimize key business processes
2. Deliver actionable insights (e.g., recommendations, scores, rules) to frontline employees and managers to help them make better decisions supporting the targeted business promesses
3. Influence customer purchase and engagement behaviours by analyzing the customer’s past purchase patterns, behaviours, and tendencies in order to deliver relevant and actionable recommendations.
4. Integrate the customer, product, and operational prescriptive analytics or recommendations back into the operational systems and management application systems.

Question 23

What is the Big Data Business Model Maturity Index?

Answer 23

A framework for organizations to measure how effective they are at leveraging data and analysis to power their business models.

Question 24

What are the four big data value drivers?

Answer 24

1. Access to all the organisation’s detailed transactional and operational data at the lowest level of granularity (at the individual customer, machine, or device level).
2. Integration of unstructured data from both internal (consumer comments, e-mail threads, technician notes) and external sources (social media, mobile, publicly available) with the detailed transactional and operational data to provide new metrics and new dimensions against which to optimize key business processes.
3. Leverage real-time (or right-time) data analysis to accelerate the organisation’s ability to identify and act on customer, product, and market opportunities in a timelier manner.
4. Apply predictive analytics and data mining to uncover customer, product, and operational insights or areas of “unusualness” buried in the massive volumes of the detailed structured and unstructured data that are worthy of further business investigation.

Question 25

Why is it important to use the next 9-to-12 month time frame with regard to the prioritization process and the big data strategy document?

Answer 25

The 9-to-12 month time frame ensures that the big data project is delivering immediate-term business value and business relevance with a sense of urgency, and it keeps the project from wandering into a "boil the ocean" type of project that is doomed to failure.

Question 26

What is data science?

Answer 26

Data science is about finding new variables and metrics that are better predictors of performance.

Question 27

What does CRISP mean in the CRISP model?

Answer 27

Cross Industry Standard Process for Data Mining.

Question 28

What are the six CRISP stages?

Answer 28

- Business Understanding - Data Understanding - Data Preparation - Modeling - Evaluation - Deployment

Question 29

What are the four steps in the Business Intelligence Analyst engagement process?

Answer 29

Step 1. Pre-build data model. Building the foundational data model. Step 2. Define the report (query) The BI analyst uses a BI tool to build the report and/ or answer the business questions. Step 3. Generate SQL commands. The BI tool generates the necessary SQL commands. Step 4. Create report. The BI tool issues the commands against the data warehouse and creates the corresponding report or dashboard widget.

Question 30

What are the six steps in the Data Scientist engagement process?

Answer 30

Step 1. Define hypothesis to test. Step 2. Gather data...and more data. Step 3. Build data model. Step 4. Visualize the data. Step 5. Build analytic models Step 6. Evaluate model Goodness of Fit

Question 31

Wat is *schema on query*?

Answer 31

The data scientist will define the schema as needed based on the data that is being used in the analysis and the requirements of the analytics tool and/or algorithm. The data scientist will likely iterate through several different versions of the schema until finding a schema that supports the analytic model with a sufficient goodness of fit that accepts or rejects the hypothesis being tested.

Question 32

In what five ways is BI different from data science?

Answer 32

- the questions are different - the analytic characteristics are different - the analytic engagement processes are different - the data models are different - the business view is different

Question 33

A business initiative supports the business strategy and has which seven characteristics?

Answer 33

1. Critical to immediate-term business and/or financial performance (usually 9-to-12 month time frame) 2. Communicated (either internally or publicly) 3. Cross-functional (involves more than one business function) 4. Owned or championed by a senior business executive 5. Has a measurable financial goal 6. Has a well-defined delivery time frame 7. Delivers compelling financial or competitive advantage

Question 34

BI questions vs data science questions. What's the difference?

Answer 34

BI focuses on descriptive analytics: that is, the "what happened?" types of questions. Data scientists focus on predictive analytics ("what is likely to happen?") and prescriptive analytics ("what should I do?") types of questions.

Question 35

What is an "analytic profile"?

Answer 35

An analytic profile is a combination of metrics, key performance indicators, scores, association rules, and analytic insight combined with the tendencies, behaviours, propensities, associations, interests and passions for an individual entity (customer, partner, device, machine).

Question 36

Name five fundamental exploratory algorithms.

Answer 36

1. Trend analysis 2. Boxplots 3. Geography (spatial) analysis 4. Pairs plot 5. Time series decomposition

Question 37

Name nine more advanced analytical algorithms.

Answer 37

1. Cluster analysis 2. Normal curve equivalant (NCE) analysis 3. Association analysis 4. Graph analysis 5. Text mining 6. Sentiment analysis 7. Traverse pattern analysis 8. Decision tree classifier analysis 9. Cohorts analysis

Question 38

Fundamental Exploratory Analytics What is trend analysis?

Answer 38

Trend analysis is a fundamental visualization technique to spot patterns, trends, relationships, and outliers across a time series of data. The mathematical models yielded by trend analysis can be used to quantify reoccusing patters or bahaviour in data.

Question 39

Fundamental Exploratory Analytics Define boxplots.

Answer 39

Boxplots are one of the most interesting and visually creative exploratory analytic algorithms. Box quickly visualize variations in the base and can be used to identify outliers in the data worthy of further investigation. A boxplot is a convenient way of graphically depicting groups of numerical data through their quartiles.

Question 40

Fundamental Exploratory Analytics Define geographical (spatial) analysis.

Answer 40

Geographical or spatial analysis includes technique for analyzing geographical activities and conditions using a business entity's topological, geometric, or geographical properties. Geographical analysis is especially useful for organizations looking to determine the success of their sales and marketing efforts.

Question 41

Fundamental Exploratory Analysis Define pairs plot.

Answer 41

Pairs plot analysis allows the data scientist to spot potential correlations using pairswise comparisons across multiple variables. Pairs plot analysis provides a deep view into the different variables that may be correlated and can form the basis for guiding the data science team in the identification of key variables or metrics to include in the development of predictive models.

Question 42

Fundamental Exploratory Analysis Define time series decomposition.

Answer 42

Time series decomposition expands on the basic trend analysis by decomposing the traditional trend analysis into three underlying components that can provide valuable customer, product, or operational performance insights. These trend analysis components are: - cyclical - seasonal - irregular

Question 43

Analytic Algorithms and Models Define cluster analysis.

Answer 43

Cluster analysis is used to uncover insights about how customers and/or products cluster into natural groupings in order to drive specific actions or recommendations. Cluster analysis or clustering is the exercise of grouping a set of objects in such a way that objects in the same group are more similar to each other than those in other groups (clusters). Cluster analysis can uncover actional insights and groups of customers and products that share the same common behavioural tendencies and, consequently, can be targeted with the same marketing treatments.

Question 44

Analytic Algorithms and Models Define Normal Curve Equivalent (NCE) analysis.

Answer 44

A technique first used in evaluating students' testing performance, normal curve equivalent (NCE), is a data transformation technique that approximately fits a normal distribution between 0 and 100 by normalizing a data set in preparation for percentile rank analysis.

Question 45

Analytic Algorithms and Models Define association analysis.

Answer 45

Association analysis is a popular algorithm for discovering and quantifying relationships betweeen variables in large databases. Association analysis shows customer or product events or activities tend to happen together, which makes this type of analysis very actionable. Association analysis is the basis for market basket analysis.

Question 46

Analytic Algorithms and Models. Define graph analysis.

Answer 46

Graph analysis is one of the more powerful analysis techniques made popular by social media analysis. Graph analysis can quickly highlight customer or machine learning relationships obscured across millions if not billions of social and machine interactions. A graph is made up of "vertices" or "nodes" and lines called edges that connect them.

Question 47

Analytic Algorithms and Models Define text mining.

Answer 47

Text mining refers to the process of deriving usuable information (metadata) from text files such as customer comments, e-mail conversations, physician notes or technician notes, ect. Basically, text mining creates structured data out of unstructured data. Text mining is a very powerful technique to show during an envisioning process.

Question 48

Analytic Algorithms and Modeling Define sentiment analysis.

Answer 48

Sentiment analysis can provide a broad general overview of your customer's sentiment toward your company and brands. Sentiment analysis can be a powerful way to glean insights about the customers' feeling about your company, products, and services out of the ever-growing body of social media sites.

Question 49

Analytic Algorithms and Modeling. Define traverse pattern analysis.

Answer 49

Traverse pattern analysis is an example of combining a couple of analytic algorithms to better understand customer, product, or operational usage patterns.

Question 50

Analytic Algorithms and Modeling. Define decision tree classifier analysis.

Answer 50

Decision tree classifier analysis uses decision trees to identify groupings and clusters buried in the usage and performance data. Decision tree classifier analysis uses a decision tree as a predictive model that maps observations about an item's target value.

Question 51

Analytic Algorithms and Modeling Define cohorts analysis.

Answer 51

Cohorts analysis is used to identify and quantify the impact that an individual or machines have on a larger group.

Question 52

What are the five characteristics that differentiate a business -ready data lake from the data warehouse?

Answer 52

1. Ingest. Capture data from wide range of traditional sources. 2. Store. Store all your data in one environment for cross-functional business analysis. 3. Analyze. Uncover new customer, product, and operational insights. 4. Surface. Empower front-line employees; drive more profitable customer engagement. 5. Act. Integrate analytic insights into operational and management systems.

Question 53

The Analytics Dilemma. What are characteristics of a BI environment?

Answer 53

1. Production 2. Predictable load 3. SLA-constrained 4. Heavily governed 5. Standard tools

Question 54

The Analytics Dilemma What are characteristic of a Analytics environment?

Answer 54

1. Exploratory, ad hoc 2. Unpredictable load 3. Experimentation 4. Loosely governed 5. Best tool for the job

Question 55

The Analytics Dilemma What is the analytics dilemma?

Answer 55

Difference between the demands for a business analytics workload and environment and a data science workload and an analytics environment.

Question 56

The Analytics Dilemma What is the solution to the analytics dilemma?

Answer 56

Put a Hadoop-based data store (data lake) in front of both the data warehouse and the analytics environment.

Question 57

Name four learnings from three decades of dealing with the limitations of the data warehouse.

Answer 57

Lesson 1. The name is not important. Inmon and Kimball approaches can both work. Lesson 2. It's a data lake, not data lakes. Having multiple data lakes will create silo's. You want to have a single repository. Lesson 3. Data governance is a lifecycle, not a project. Different degrees of governance: highly governed, moderately governed, ungoverned data Lesson 4. Data lake sits before the data warehouse, not after it.

Question 58

Define the three degrees of data governance in the data lake.

Answer 58

- Highly governed data - Moderately governed data - Ungoverned data The goal should be just-enough governed data.

Question 59

Define the characteristics of a key business initiative.

Answer 59

1. Critical to the immediate-term performance of the organization. 2. Documented (communicated either internally or publicly). 3. Cross-functional (involves more than one business function 4. Owned and championed by a senior business executive 5. Has a measurable financial goal 6. Has a well-defined delivery time frame (9-12 months) 7. Undertaken to deliver significant, compelling an differentiated competitive advantage.

Question 60

What are the six steps in the monetization exercise process?

Answer 60

Step 1. Understand product usage characteristics and behaviours Step 2. Develop personas for each customer type (including key decisions and pain points) Step 3. Brainstorm potential customer recommendations Step 4. Identify supporting data sources Step 5. Prioritize monetization opportunities (revenues) Step 6. Develop monetization plan.

Question 61

What are the steps in the metamorphosis exercise?

Answer 61

Step 1. Articulate metamorphosis vision Step 2. Understand your customers Step 3. Articulate value propositions Step 4. Define data and analytic requirements

Question 62

What are the key components in creating a compelling story that is relevant and unique for your organisation?

Answer 62

1. Key business initiative 2. Strategic nouns or key business entities 3. Current challenging situation 4. Creative solution 5. Desired glorious end state

Question 63

What does the Big Data Business Model Maturity Index measure?

Answer 63

It measures the degree to which the organization has integrated data and analytics into their business models.

Question 64

What is "comparative parity"?

Answer 64

Is achieving similar or same operational capabilities as those of your competitors. It involves leveraging industry best practices and pre-packaged software to create a baseline that, at worst, is equal to the operational capabilities across your industry.

Question 65

What is "comparative differentiation"?

Answer 65

Is achieved when an organisation leverages people, processes, and technology to create applications, programs, processes, etc., that differentiate its products and services from those of its competitors in ways that add unique value for end customer and create competitive differentiation in the marketplace.

Question 66

Why is analytics a comparative differentiator?

Answer 66

Analytics enables organisations to uniquely optimize their key business processes, drive a more engaging customer experience, and uncover new monetization opportunities with unique insights that they gather about their customers, products, and operations.

Question 67

What is the first question that organisations need to ask themselves about big data?

Answer 67

How effective is my organisation at leveraging new sources of data and advances analytics to uncover new customer, product, and operational insights that can be and uncover new monetization opportunities?

Question 68

What is the key to big data success?

Answer 68

The key to big data success is empowering cross-functional collaboration and exploratory thinking to challenge long-held organisational rules of thumb, heuristics, and "gut" decision making. The business needs an approach that is inclusive of all the key stakeholders - IT, business users, business management, channel partners, and ultimately customers. The business potential of big data is only limited by the creative thinking of the organisation.

Question 69

What can big data potentially do for an organisation?

Answer 69

Big data has the potential to uncover new customer, product, and operational insights that organisations can use to optimize key business processes, improve customer engagement, uncover new monetization opportunities, and re-wire the organisation's value creation processes.

Question 70

Where lies the focus of BI?

Answer 70

BI focuses on descriptive analytics: that is, the "What happened?" types of questions. It focuses on reporting the current state of the business, or as it is now commonly calles Business Performance Management (BPM). BI provides retrospective reports to help business users to monitor the current state of the reports and questions are critical to the business, sometimes required for regulatory and compliance reasons.

Question 71

Where lies the focus of Data Science?

Answer 71

Data scientists are in search of variables and metrics that are better predictors of business performance. Consequently, data scientists focus on predictive analytics and prescriptive analytics types of questions. To answer these predictive and prescriptive questions, data scientists build analytic models in an attempt to quantify cause and effect,

Question 72

The approach to data science consists of what stages?

Answer 72

1. Establish a business hypothesis or question 2. Explore different combinations of data and analytics to build, test, and refine the model 3. Wash, rinse, and repeat until the model proves that it can provide the required "analytic lift" while reaching a satisfactory goodness of fit 4. The analytics are deployed or operationalized including possibly rewriting the analytics in a different language to speed the model execution and integrating the analytic models and results into the organisation's operational and management systems.

Question 73

Exploratory analytics algorithms is best exemplified by which of the following? A. Trend Analysis B. Geographical Analytics C. Box plots D. Pair plots E. All

Answer 73

E. All

Question 74

Where does the Big Data Business Model Maturity Index provide the roadmap for?

Answer 74

1. How organisations can integrate *data* into their business models 2. How organisations can integrate *analytics* into their business models

Question 75

The concept of clustering is very frequently applied to one of the areas mentioned below. Identify which one. A. Food and hygiene B. Sound engineering C. Image Compression D. Memory utilization

Answer 75

C. Image Compression

Question 76

What is “competitive parity”?

Answer 76

*Competitive parity* is achieving similar or same operational capabilities as those of your competitors. It involves leveraging industry best practises and pre-packaged software to create a baseline that, at worst, is equal to the operational capabilities actoss your industry.

Question 77

What is “competitive differentiation”?

Answer 77

*Competitive differentiation* is achieved when an organisation leverages people, processes, and technology to create applications, programmes, processes, etc., that differentiate its products and services from those of its competitors in ways that add unique valur for the end customer and create competitive differentiation in the marketplace.

Question 78

The economics of big data enable four new capabilities that will help the organisation cross the analytics chasm and move beyond the Business Monitoring phase into the Business Insights phase. Which four big data value drivers?

Answer 78

1. Access to *all* the organisation’s transactional and operational data. 2. Access to internal and external unstructured data. 3. Exploiting real-time analytics. 4. Integrating predictive analytics.

Question 79

What are three monetization opportunities in the data monetizations stage?

Answer 79

1. Packaging data (with analytics insights) for sale to other organisations. 2. Integrating analytics insights directly into an organisation’s products and services to create “intelligent” products or services. 3. Repackaging insights to create entirely new products and services that help organisations enter new markets and target new customers or audiences.

Question 80

What are the eight steps in “thinking like a data scientist”?

Answer 80

Step 1: Identify key business initiative Step 2: Develop business stakeholder persona Step 3: Identify strategic nouns Step 4: Capture business decisions Step 5: Brainstorm business questions Step 6: Leverage “By” analysis Step 7: Create actionable scores Step 8: Putting analytics into action

Question 81

What is the core of the “by” analysis?

Answer 81

*”I want to [verb] [metric] by [dimensional attribute]”*

Question 82

What is the *monetization exercise*?

Answer 82

The monetization exercise seeks to understand how the organisation’s product or services are used by its customers, and then identify how the customer and product usage data can be used to create new monetization opportunities. The monetization exercise provides an opportunity to uncover new product and/or service opportunities through the identification and delivery of new customer and frontline employee recommendations. The monetization exercise works by first understanding the product usage patterns and customer usage behaviours associated with a particular product or service. The process then seeks to identify complementary or secondary recommendations that can be packaged and delivered along with that product or service.

Question 83

Define the six steps in the monetization exercise process.

Answer 83

Step 1: Understand product usage characteristics and behaviours. Step 2: Develop personas for each customer type Step 3: Brainstorm potential customer recommendations Step 4: Identify supporting data sources Step 5: Prioritize monetization opportunities Step 6: Develop monetization plan

Question 84

What is the timeline and the process of the Big Data Vision Workshop?

Answer 84

- Research - Interview - Explore - Workshop - Recommend

Question 85

What are examples of deliverables from a Big Data Vision Workshop?

Answer 85

- Prioritization matrix with the prioritization of the use cases - The sticky note content for each use case - Interview takeaways - Data scientist illustrative analytics - User experience mock-ups - Documentation of the Parking Lot items (for potential follow-up) - Data assessment worksheets that assess the business value and implementation feasibility of each data source.

Question 86

What is the *prioritization matrix* a great tool for?

Answer 86

- Identifying the “right” use case to pursue with big data based on a balance of business value and implementation feasibility. - Ensuring that both IT and business stakeholders have a voice in discussing the relative value and implementation challenges for each use case. - Capturing the business drivers and implementation risks for each of the use cases. - Catalyzing the decision on the “right” use cases so that everyone (business and IT) can agree on a path forward.

Question 87

What are the two axis of the *prioritization matrix*?

Answer 87

Y = Business Value X = Implementation Feasibility

Question 88

Analytics Center of Excellence The analytics Center of Excellence (COE) is critical to the success of the CDMO's data monetization charter and needs to be the responsibility of the CDMO. Key CDMO taks with respect to the COE include?

Answer 88

- Hiring, development, promotion, retention, and talent management of the data science and Business Intelligence teams (even if they do sit within the business units) - Continuous training program and certification on new technologies and analytic algorithms - Active industry and university monitoring to stay on top of most current data and data science trends. - Business intelligence, data visualization, statistical, predictive analytics, machine learning and data mining tool evaluations and recommendations. - Capturing, sharing, and management (i.e., library function) of the Business Intelligence, data warehousing, and data science best practises across the organisaton. - Identifying analytic processes worthy of legal or patent protection.

Question 89

The *empowerment cycle* empowers organisations to freely consider different ideas without worying about whether the ideas are correct ahead of time. What are the steps in the *empowerment cycle*?

Answer 89

Step 1: Develop hypothesis or hunch to test. Step 2: Develop test cases to test hypothesis or hunch. Step 3: Instrument all test cases to measure results. Step 4: Execute and measure test results. Step 5: Learn and move on.