Data Science Basics

Data Science is

• The science of creating data.

• It is a branch of Social Studies.

• Multidisciplinary study of data collections for analysis, prediction, learning and prevention.

• It is a specialized field of study under Artificlal Intelligence

Steps in Data Science

• Data Modeling ->Data Acquisition -> Clean Data ->Data Analysis ->Deployment and optimization

• Data Acquisition -> Clean Data ->Data Analysis -> Data Modeling ->Deployment and optimization

• Clean Data ->Data Analysis -> Data Modeling ->Deployment and optimization -> Data Acquisition

• Data Modeling ->Data Acquisition -> Clean Data ->Data Analysis ->Deployment and optimization

In Data Acquisition stage which deals with Type and Source of Data, following data sources are correct.

• User and Inventory data from transaction databases.

• Social Engagement from Social Networks like Facebook Twitter.

• Training Data from from tools like CrowdFlower, Mechanical Turk.

• Customer Support data from Call Logs, Emails

Data integration involves combining data residing in different sources and providing users with a unified view of these data.

• True

• False

Data are often incomplete, incorrect. Some of possible values in incorrect data can be

• Typo : e.g., text data in numeric fields

• Out-of-Range Values: e.g., age=1000

• Missing Values : some fields may not be collected for some of the examples

• Extra spaces in text data.

In Data Analysis stage of Data preparation following are correct.

• Univariate Analysis: Analyze/explore variables one by one

• Bivariate Analysis: Explore relationship between variables

• Statistical Analysis: Deriving inferences from mean,median and mode.

• Feature Engineering: Variable transformations and creation of new better variables from raw features.

Predictive data modeling involves the collection of data on consumer behaviour to predict future consumer behaviour and to take action accordingly. Following are the valid examples of the same.

• Recommendation systems (netflix, pandora, amazon, etc.)

• Payroll data in the organization.

• Online user behaviour is used to predict best targeted ads

• Customer purchase histories are used to determine how to price,stock, market and display future products.

Machine Learning is the study of algorithms that improve their performance at some task with example data or past experience. It is made up of 3 major parts which are

• Model ,Parameters and Learner.

• Model, Source and Parameters.

• Source, Parameters and Algorithms.

• Model , Parameters and Algorithms.

Following are the valid examples of Machine learning application.

• Association Analysis

• Supervised Learning

• Unsupervised Learning

• Inverse Analysis

Deployed solutions might include:

• A trained data model (model + parameters)

• Routines for inputting and prediction

• Routines for model improvement

• Routines for training

• Decision Support System.