Concepts of Data Analytics

data

individual facts, figures, signals, measurement raw, unanalyzed, unorganized material

knowledge

information + meaning idea, learning, notion, concept, thought out

wisdom

knowledge + insight understanding, integration, principles

supervised learning

learning a function that maps an input to an output based on example input/output pairs Y = f(x) logistical regression decision tree

test set

measure performance of the selected model on unseen data not always used estimate

analytics are often used

new customer acquisition cross and up sell pricing tolerance supply optimization staffing optimization financial forecasting product placement churn insurance rate sets fraud detection

importance of business analytics

profitability revenue shareholder return understanding of data vital for businesses to remain competitive enables creation of informative reports

interval/ratio data

scale data numerical format measured on continuous scale can be placed in rank order interval scale have no true zero ratio scale does have a true zero ratio has exact value and absolute zero

validation set

select the best model during training avoid overfitting

important trends

storage capacity continues to rise rapidly cost of storage continues to drop

business analytics

subset of data analytics

unsupervised learning

type of ML algorithms used to draw inferences from datasets consisting of input data without labeled responses

variable

unit of data collection whose value can vary

challenges in decision making

we do not know everything huge amount of data mistake can cause disaster uncertainty

analytical landscape

analytical modelers to proliferation of models to operations to target

machine learning

artificial intelligence scientific study of algorithms and statistical models that computer systems use to perform a specific task without using explicit instructions, relying on learning patterns and inferences from examples instead

information

data + context organized, structured, categorized

analytics

data, information technology, statistical analysis, quantitative methods, mathematical/computer methods

utilizing business data

determine business needs capture and store data ensure quality access and format analyze and summarize gain insight and produce action

training set

To find patterns and create an initial set of candidate models

business intelligence

a broad category of applications, technologies, and processes for gathering, storing, accessing, and analyzing data to help business users make better decisions

ordinal data

can be rank ordered no fixed units of measurement can make statistical judgements ex. socio econ. status or military ranks

four types of data

categorical, ordinal, interval, ratio

decision making

choice about a course of action

categorical/nominal data

comprised of categories that cannot be rank ordered each category is just different no quantitative relationship no mathematical operations mutually exclusive exhaustive ex. customers location or different colleges at univ.

data mining

computational process of discovering patterns in large data sets involving methods at the intersection of artificial intelligence, machine learning, statistics and database systems customer segmentation (clustering) predictive modeling associate rule mining