Chapter 1: Data Analytics Flashcards
(24 cards)
Data Analytics
What are the key technologies of big data?
- Data mining
- Text mining: Analyzes text-based data from websites, comment fields, books
- Data management
- In-memory analytics
- Predictive analytics
- Hadoop: a third-party provider that stores large amounts of data
Data Analytics
What is data mining?
- Data mining drills down the data to remove any repetitive patterns
- Uses both qualitative and quantitative methods to retrieve data
- It then finds unexpected data that to determine if there are any issues (i.e. fraudulent transactions,correaltions of unrelated data, etc.)
Data Analytics
What is in-memory analytics?
- In-memory analytics uses data that is used from system memory instead of the hard drives
- This is because the data that is in the system can be backed-up on a regular basis, while hard drives may have data that is not saved onto the system, but on the computers C: drive
Data Analytics
What is Diagnostic Analysis?
- What happened that caused the results to occur?
- Uses historical information to provide insight
Data Analytics
What is Descriptive Analytics?
- What Happened?
- The most basic and commonly used analytic
- Reports on actual results from historical information
Data Analytics
What are the different types of descriptive analytics?
- Review historical information to see if there are relationships and trends and to find out why trends happen
- Anomoly detection
- Regression analysis
Data analtyics
Why is anomaly detection considered a component of descriptive analysis?
- Anamoly detection is reported
- Once all of the historical data mining, extraction and cleaning has been done, the data is the reviewed and analyzed to determine if there are any unusual patterns or deviations from the expected results
Data Analytics
What is Predictive Analytics?
- What happened in the past that will have a result in the future and can be predicted?
- What will happen next?
- What is the expected outcome of the result?
- Predictive Analytics applies assumptions of data from various technology sources to find different outcomes from future events
Data Analytics
What types of technology can be used in predictive analysis?
- Data mining
- Statistical algorythms
- Machine-learning techniques
- Predictive modeling to cluster analysis groups of data with similar characteristics
Data Analytics
What is Prescriptive Analysis?
- What should be done in the future in order for the results to occur?
- Based on future results, not historical information
- Occurs when a plan is put into place (i.e. increase sales by 20%)
- It is the most complex analysis because it uses all of the analysis tools, diagnostic, descriptive and predictive analytics to improve business strategy
- Provides the most data inputs
Data Analytics
What is ranking of data size?
“Kim Met Gene To Purchase Extra Zebra Yarn”
- Kilobyte
- Megabyte
- Gigabyte
- Terabyte
- Petabyte
- Exabyte
- Zettabyte
- Yottabyte
Implementing Data Analytics
What are the five stages of data analytics?
“DOC-AC”
* Define business questions to determine the goals and objectives that need to be obtained
* Obtain relevant data through information discovery
* Clean/scrub/normalize data
* Analyze data to derive values
* Communicate results including information used, conclusions and recommendations
Data Visualization
What are the elements of data visualization?
- Title: Shows the reader the expected subject
- Axis: The data and the axis label is measured and presented
- Presentation: The reader can determine what and how to look for information
- Legends: Additional information to help the reader understand the visualization
Data Visualization
When would a pie chart be used?
- Pie charts use all the data in the graph
- The data is used to show relative proportions of a specific period
Data Visualization
When would a scatter-plot chart be used?
Scatter plots are used to show the relationship between two variables
Data Visualization
When would a line chart be used?
- Line charts are used to show trends, cycle or variability over time
- They are similar to bar graphs, but they are dots are shown instead of bar height
Data Visualization
When would a stack-bar graph be used?
Stacked bar graphs are used to show the comparison in a item and changes of components over time
Data Visualization
When would a bubble chart be used?
- Bubble charts are similiar to scatter plots
- They include a third variable that is shown as the size in data points
Data Visualization
When would a dot-map chart be used?
Dot maps are used to summarize the density of the data
Data Visualization
When would a historgram be used?
Histograms are used to summarize the distribution of data
Data Visualization
When will a table chart be used?
Tables are used to present the data as close to the original form, as well as including the details of the data
Data Visualization
When would a treemap be used?
- Treemaps are based on rectangles of different colors and sizes.
- The colors represent the category of data and the size reports the value
Data Visualization
When would a fishbone diagram be used?
- Fishbone diagram is known as the cause and effect diagram
- It organizes the analysis of the causes and helps identify their possible interactions
Data Visualization
When would a stastical control chart be used?
A statistical control chart provides more visibility to trends and cycles that are outside of the control area
