Data Science Training using SAS

Introduction to the Analytics world and SAS role

Analytics World
- Introduction to Analytics
- ETL CONCEPT and role of SAS in ETL
- SAS in advanced analytics
SAS Certification: Induction and walk through
- Getting Started with SAS
- SAS software installation
- Introduction to SAS, GUI
- Different components of SAS language
- All SAS programming windows
- Concept of SAS Libraries and Creating Libraries
- Variable Attributes - (Name, Type, Length, Format, In format, Label)
- Importing Data and Entering data manually
Understanding Datasets
- Descriptor Portion of a Dataset (Proc Contents)
- Data Portion of a SAS Dataset
- Variable Names and Values
- SAS Data Libraries

Base SAS - Accessing the Data

Understanding Data Step Processing
- Data Step and Proc Step
- Data step execution
- Compilation and execution phase
- Input buffer and concept of PDV
Importing Raw Data Files
- Column Input and List Input and Formatted methods
- Delimiters, Reading missing and non standard values
- Reading one to many and many to one records
- Reading Hierarchical files
- Creating raw data files and put statement
- Formats / Informat
Importing and Exporting Data (Fixed Format / Delimited)
Proc Import / Delimited text files
Proc Export / Exporting Data from SAS
Datalines / Cards;
Atypical importing cases (mixing different style of inputs)
- Reading Multiple Records per Observation
- Reading “Mixed Record Types”
- Sub-setting from a Raw Data File
- Multiple Observations per Record
- Reading Hierarchical Files
Importing Tips

Base SAS - Data Understanding, Managing and Manipulation

Understanding and Exploration Data
- Introduction to basic Procedures - Proc Contents, Proc Print
Understanding and Exploration Data
- Operators and Operands
- Conditional Statements (Where, If, If then Else, If then Do and select when)
- Difference between WHERE and IF statements and limitation of WHERE statements
- SAS Labels, Commenting
- SAS System Options (OBS, FSTOBS, NOOBS etc…)
Data Manipulation
- Proc Sort - with options / De-Duping
- Accumulator variable and By-Group processing
- Explicit Output Statements
- Nesting Do loops
- Do While and Do Until Statement
- Array elements and Range
Combining Datasets (Appending and Merging)
- Concatenation
- Interleaving
- Proc Append
- One To One Merging
- Match Merging
- IN = Controlling SAS merge and Indicator

Advance SAS - Data Mining with Proc SQL

Introduction to Databases
Introduction to Proc SQL
Basics of General SQL language
Creating table and Inserting Values
Retrieve & Summarize data
Group, Sort & Filter
Using Joins (Full, Inner, Left, Right and Outer)
Reporting and summary analysis
Concept of Indexes and creating Indexes (simple and composite)
Connecting SAS to external Databases
Implicit and Explicit pass through methods

Advanced SAS - SAS Macros

Macro Parameters and Variables
Different types of Macro Creation
Defining and calling a macro
Using call Symput and Symget
Macros options (mprint symbolgen mlogic merror serror)

Introduction to Data Science with R

What is analytics & Data Science?
Common Terms in Analytics
Analytics vs. Data warehousing, OLAP, MIS Reporting
Relevance in industry and need of the hour
Types of problems and business objectives in various industries
How leading companies are harnessing the power of analytics?
Critical success drivers
Overview of analytics tools & their popularity
Analytics Methodology & problem solving framework
List of steps in Analytics projects
Identify the most appropriate solution design for the given problem statement
Project plan for Analytics project & key milestones based on effort estimates
Build Resource plan for analytics project
Why R for data science?

R- Introduction - Data Importing/Exporting

Introduction R/R-Studio - GUI
Concept of Packages - Useful Packages (Base & Other packages)
Data Structure & Data Types (Vectors, Matrices, factors, Data frames, and Lists)
Importing Data from various sources (txt, dlm, excel, sas7bdata, db, etc.)
Database Input (Connecting to database)
Exporting Data to various formats)
Viewing Data (Viewing partial data and full data)
Variable & Value Labels – Date Values

R - Data Manipulation steps

Creating New Variables (calculations & Binning)
Dummy variable creation
Applying transformations
Handling duplicates
Handling missings
Sorting and Filtering
Subsetting (Rows/Columns)
Appending (Row appending/column appending)
Merging/Joining (Left, right, inner, full, outer etc)
Data type conversions
Renaming
Formatting
Reshaping data
Sampling

R- Data Manipulation tools

Operators
Functions
Packages
Control Structures (if, if else)
Loops (Conditional, iterative loops, apply functions)
Arrays

R - Data Manipulation functions

R Built-in Functions (Text, Numeric, Date, utility)
- Numerical Functions
- Text Functions
- Date Functions
- Utilities Functions
R User Defined Functions
R Packages for data manipulation (base, dplyr, plyr, data.table, reshape, car, sqldf, etc)

R - Data Analysis - Visualization

Introduction exploratory data analysis
Descriptive statistics, Frequency Tables and summarization
Univariate Analysis (Distribution of data & Graphical Analysis)
Bivariate Analysis(Cross Tabs, Distributions & Relationships, Graphical Analysis)
Creating Graphs- Bar/pie/line chart/histogram/boxplot/scatter/density etc)
R Packages for Exploratory Data Analysis(dplyr, plyr, gmodes, car, vcd, Hmisc, psych, doby etc)
R Packages for Graphical Analysis (base, ggplot, lattice etc)

Introduction to Statistics (R)

Basic Statistics - Measures of Central Tendencies and Variance
Building blocks - Probability Distributions - Normal distribution - Central Limit Theorem
Inferential Statistics -Sampling - Concept of Hypothesis Testing
Statistical Methods - Z/t-tests (One sample, independent, paired), Anova, Correlations and Chi-square

Predictive Modeling - Introduction (R)

Concept of model in analytics and how it is used?
Common terminology used in analytics & modeling process
Popular modeling algorithms
Types of Business problems - Mapping of Techniques
Different Phases of Predictive Modeling

Data Preparation for Modeling (R)

Need for structured exploratory data
EDA framework for exploring the data and identifying any problems with the data (Data Audit Report)
Identify missing data
Identify outliers data
Visualize the data trends and patterns
Need of Data preparation
Consolidation/Aggregation - Outlier treatment - Flat Liners - Missing values- Dummy creation - Variable Reduction
Variable Reduction Techniques - Factor & PCA Analysis

Segmentation: Solving segmentation problems (R)

Introduction to Segmentation
Types of Segmentation (Subjective Vs Objective, Heuristic Vs. Statistical)
Heuristic Segmentation Techniques (Value Based, RFM
Segmentation and Life Stage Segmentation)
Behavioral Segmentation Techniques (K-Means Cluster Analysis)
Cluster evaluation and profiling - Identify cluster characteristics
Interpretation of results - Implementation on new data

Linear Regression: Solving regression problems (R)

Introduction - Applications
Assumptions of Linear Regression
Building Linear Regression Model
Understanding standard metrics (Variable significance, R-square/Adjusted R-square, Global hypothesis ,etc)
Assess the overall effectiveness of the model
Validation of Models (Re running Vs. Scoring)
Standard Business Outputs (Decile Analysis, Error distribution (histogram), Model equation, drivers etc.)
Interpretation of Results - Business Validation -
Implementation on new data

Logistic Regression: Solving classification problems (R)

Introduction - Applications
Linear Regression Vs. Logistic Regression Vs. Generalized Linear Models
Building Logistic Regression Model (Binary Logistic Model)
Understanding standard model metrics (Concordance,
Variable significance, Hosmer Lemeshov Test, Gini, KS, Misclassification, ROC Curve etc)
Validation of Logistic Regression Models (Re running Vs. Scoring)
Standard Business Outputs (Decile Analysis, ROC Curve, Probability Cut-offs, Lift charts, Model equation, Drivers or variable importance, etc)
Interpretation of Results - Business Validation -
Implementation on new data

Time Series Forecasting: Solving forecasting problems (R)

Introduction - Applications
Time Series Components( Trend, Seasonality, Cyclicity and Level) and Decomposition
Classification of Techniques(Pattern based - Pattern less)
Basic Techniques - Averages, Smoothening, etc
Advanced Techniques - AR Models, ARIMA, etc
Understanding Forecasting Accuracy - MAPE, MAD, MSE, etc

Machine Learning -Predictive Modeling – Basics (R)

Introduction to Machine Learning & Predictive Modeling
Types of Business problems - Mapping of Techniques -Regression vs. classification vs. segmentation vs. Forecasting
Major Classes of Learning Algorithms -Supervised vs Unsupervised Learning
Different Phases of Predictive Modeling (Data Pre-processing, Sampling, Model Building, Validation)
Overfitting (Bias-Variance Trade off) & Performance Metrics
Feature engineering & dimension reduction
Concept of optimization & cost function
Overview of gradient descent algorithm
Overview of Cross validation(Bootstrapping, K-Fold validation etc)
Model performance metrics (R-square, Adjusted R-squre, RMSE, MAPE, AUC, ROC curve, recall, precision, sensitivity, specificity, confusion metrics )

Unsupervised Learning: Segmentation (R)

What is segmentation & Role of ML in Segmentation?
Concept of Distance and related math background
K-Means Clustering
Expectation Maximization
Hierarchical Clustering
Spectral Clustering (DBSCAN)
Principle component Analysis (PCA)

Supervised Learning: Decision Trees (R)

Decision Trees - Introduction - Applications
Types of Decision Tree Algorithms
Construction of Decision Trees through Simplified Examples; Choosing the "Best" attribute at each Non-Leaf node; Entropy; Information Gain, Gini Index, Chi Square, Regression Trees
Generalizing Decision Trees; Information Content and Gain Ratio; Dealing with Numerical Variables; other Measures of Randomness
Pruning a Decision Tree; Cost as a consideration; Unwrapping Trees as Rules
Decision Trees - Validation
Overfitting - Best Practices to avoid

Supervised Learning: Ensemble Learning (R)

Concept of Ensembling
Manual Ensembling Vs. Automated Ensembling
Methods of Ensembling (Stacking, Mixture of Experts)
Bagging (Logic, Practical Applications)
Random forest (Logic, Practical Applications)
Boosting (Logic, Practical Applications)
Ada Boost
Gradient Boosting Machines (GBM)
XGBoost

Supervised Learning: Artificial Neural Networks (ANN) (R)

Motivation for Neural Networks and Its Applications
Perceptron and Single Layer Neural Network, and Hand Calculations
Learning In a Multi Layered Neural Net: Back Propagation and Conjugant Gradient Techniques
Neural Networks for Regression
Neural Networks for Classification
Interpretation of Outputs and Fine tune the models with hyper parameters
Validating ANN models

Supervised Learning: Support Vector Machines (R)

Motivation for Support Vector Machine & Applications
Support Vector Regression
Support vector classifier (Linear & Non-Linear)
Mathematical Intuition (Kernel Methods Revisited,
Quadratic Optimization and Soft Constraints)
Interpretation of Outputs and Fine tune the models with hyper parameters
Validating SVM models

Supervised Learning: KNN (R)

What is KNN & Applications?
KNN for missing treatment
KNN For solving regression problems
KNN for solving classification problems
Validating KNN model
Model fine tuning with hyper parameters

Supervised Learning: Naïve Bayes (R)

Concept of Conditional Probability
Bayes Theorem and Its Applications
Naïve Bayes for classification
Applications of Naïve Bayes in Classifications

Text Mining & Analytics (R)

Taming big text, Unstructured vs. Semi-structured Data;
Fundamentals of information retrieval, Properties of words; Creating Term-Document (TxD);Matrices; Similarity measures, Low-level processes (Sentence Splitting; Tokenization; Part-of-Speech Tagging; Stemming; Chunking)
Finding patterns in text: text mining, text as a graph
Natural Language processing (NLP)
Text Analytics – Sentiment Analysis using R
Text Analytics – Word cloud analysis using R
Text Analytics - Segmentation using K-Means/Hierarchical Clustering
Text Analytics - Classification (Spam/Not spam)
Applications of Social Media Analytics
Metrics(Measures Actions) in social media analytics
Examples & Actionable Insights using Social Media Analytics

Important R packages for Machine Learning (caret, H2O, Randomforest, nnet, tm etc)

Fine tuning the models using Hyper parameters, grid search, piping etc.

Introduction to Statistics (SAS - Video- Based)

Basic Statistics - Measures of Central Tendencies and Variance
Building blocks - Probability Distributions - Normal distribution - Central Limit Theorem
Inferential Statistics -Sampling - Concept of Hypothesis Testing
Statistical Methods - Z/t-tests( One sample, independent, paired), Anova, Correlations and Chi-square

Introduction to Predictive Modeling (SAS - Video- Based)

Introduction to Predictive Modeling
Types of Business problems - Mapping of Techniques
Different Phases of Predictive Modeling

Data Preparation (SAS - Video- Based)

Need of Data preparation
Data Audit Report and Its importance
Consolidation/Aggregation - Outlier treatment - Flat Liners - Missing values- Dummy creation - Variable Reduction
Variable Reduction Techniques - Factor & PCA Analysis

Segmentation (SAS - Video- Based)

Introduction to Segmentation
Types of Segmentation (Subjective Vs Objective, Heuristic Vs. Statistical)
Heuristic Segmentation Techniques (Value Based, RFM Segmentation and Life Stage Segmentation)
Behavioural Segmentation Techniques (K-Means Cluster Analysis)
Cluster evaluation and profiling
Interpretation of results - Implementation on new data

Linear Regression (SAS - Video- Based)

Introduction - Applications
Assumptions of Linear Regression
Building Linear Regression Model
Understanding standard metrics (Variable significance, R-square/Adjusted R-square, Global hypothesis ,etc)
Validation of Models (Re running Vs. Scoring)
Standard Business Outputs (Decile Analysis, Error distribution (histogram), Model equation, drivers etc.)
Interpretation of Results - Business Validation - Implementation on new data

Logistic Regression (SAS - Video- Based)

Introduction - Applications
Linear Regression Vs. Logistic Regression Vs. Generalized Linear Models
Building Logistic Regression Model
Understanding standard model metrics (Concordance, Variable significance, Hosmer Lemeshov Test, Gini, KS, Misclassification, etc)
Validation of Logistic Regression Models (Re running Vs. Scoring)
Standard Business Outputs (Decile Analysis, ROC Curve,
Probability Cut-offs, Lift charts, Model equation, Drivers, etc)
Interpretation of Results - Business Validation -Implementation on new data

Travel Flights Analysis (SAS)

Study the flights data along with their schedules, weather and also plane information thereby understanding flight routes and delays. This case study comprises of four sections (Import and understand the data, Preparing data for analysis, Perform exploratory analysis, forming & testing hypothesis etc)

Laptop Sales Analysis (SAS)

Data mining the sales transaction data using SAS to find key sales trends.

Banking Case study (R)

Understand customer spend & repayment behavior, along with evaluating areas of bankruptcy, fraud, and collections. Also, respond to customer requests for help with proactive offers and service.

Visualization (R)

Perform different graphical analysis (bar chart, pie chart, box plot, histogram, stacked charts, heat maps, scatter plots, panel charts etc) for solving various business problems

Credit Card Customers Segmentation (SAS & R)

A credit card company wishes to understand its customer behavior so to have an enriched customer profile by having intelligent KPI’s. The idea is to apply advanced algorithms like factor and cluster analysis for data reduction and customer segmentation based on the behavioral data.

Proactive Attrition Management (SAS & R)

A wireless telecom companies wants to reduce customer churn by developing a proactive churn management model. The idea is to build a logistic regression based predictive model to develop an incentive plan for enticing would-be churners to remain with the company.

Predicting Loan Default (SAS & R)

A bank would like to build credit risk model (application score card using PD models) to accept/ reject applications for loans. Also it wants to understand the key drivers for default or delinquency.

Key Drivers for Customer credit card spending (SAS & R)

The objective of this case study is to understand what's driving the total spend of credit card(Primary Card + Secondary card) and identify the key spend drivers . This will require candidates to apply OLS/ linear regression and follow end-to-end model building process and help set the credit limit and designing new product offerings.

Time Series Forecasting (R)

Use time series analysis to forecast the outbound passenger movement for next few quarters.

Sentiment Analysis (R)

Objective of this analysis is to obtain data from Twitter and check how the sentiment varies by country for a particular brand/keyword/company.

Access to 108 hours instructor led live classes of 24x3 hours each, spread over 18 weekends, apart from 18 hours of video content

Video recordings of the class sessions for self study purpose

Weekly assignment, reference codes and study material in PDF format

Module wise case studies/ projects

Specially curated study material and sample question for SAS Global Certification

Career guidance and career support post the completion of some selected assignments and case studies

What if I miss a class?

Don’t worry. You will always get a recording for the class in your Learning Management System (LMS) account. Have a look at that and reach out to the faculty in case of doubts. All our live classes are recorded for self-study purpose and future reference, and these can also be accessed through our LMS. Hence, in case you miss a class, you can refer to the video recording and then reach out to the faculty during their doubts clearing time or ask your question in the beginning of the subsequent class.

You can also repeat any class you want in the next one year after your course completion. Batch change policies will however, apply in this case.

Please note that incase you are not able to complete your course within one year of course validity, due to reasons at your end, limited support might be available post the completion of one year.

For how long are the recordings available to me?

1 year post your course commencement. If needed, you can also repeat any number of classes you want in the next one year after course completion. Batch change policies will however, apply in this case.

In case required because any genuine reasons, the recordings access can be extended further for upto 1 year post the completion of one year validity. Please note that given the constant changes in the Analytics industry, our courses continue to be upgraded and hence old courses might no longer hold relevance. Hence, we do not promise lifetime access just for marketing purposes.

Can I download the recordings?

No. Our recordings can be accessed through your account on LMS or stream them live online at any point of time though.

Recordings are integral part of AnalytixLabs intellectual property by Suo Jure. The downloading/distribution of these recordings in anyway is strictly prohibited and illegal as they are protected under copyright act. Incase a student is found doing the same, it will lead to an immediate and permanent suspension in the services, access to all the learning resources will be blocked, course fee will be forfeited and the institute will have all the rights to take strict legal action against the individual.

What if I share my LMS login details with a friend?

The sharing of LMS login credentials is unauthorized, and as a security measure, if the LMS is accessed by multiple places, it will flag in the system and your access to LMS can be terminated.

Will I get a certificate in the end?

Yes. All our course are certified. As part of the course, students get weekly assignments and module-wise case studies. Once all your submissions are received and evaluated well, the certificate shall be awarded.

Please note that incase you are not able to complete the course within the one year validity, AnalytixLabs might hold a mock interview/viva, apart from your submissions, before issuing the certificate.

Do you help in placements?

We follow a comprehensive and a self-sustaining system to help our students with placements. This is a win-win situation for our candidates and corporate clients. As a pre-requisite for learning validation, candidates are required to submit the case studies and project work provided as a part of the course (flexible deadline). Support from our side is continuous and encompasses help in profile building, CV referrals (as and when applicable) through our ex-students, HR consultants and companies directly reaching out to us.

We will provide guidance to you in terms of what are the right profiles for you based on your education and experience, interview preparation and conducting mock interviews, if required. The placement process for us doesn’t end at a definite time post your course completion, but is a long relationship that we will like to build.

To avoid any kind of ambiguity, we strongly suggest that you go through our course brochures.

Please also note that incase you are unable to complete the course in the one year course validity period, we might not be able to assist with placements. The discussion you would have had with our counsellors/faculty at the time of registration is also basis the profile you hold at that time. Incase your course has got delayed due to reasons at your end, this might effect the profile, in which case it might be difficult for us to assist in placements.

Do you guarantee placements?

No institute can guarantee placements, unless they are doing so as a marketing gimmick! It is on a best effort basis.

In professional environment, it is not feasible for any institute to do so, except for a marketing gimmick. For us, it is on a best effort basis but not time – bound – in some cases students reach out to us even after 3 years for career support.

Do you have a classroom option?

Yes we have classroom option for Delhi-NCR and Bengaluru candidates. However, most of our students end up doing instructor led live online classes, including those who join classroom in the beginning. Based on the student feedback, the learning experience is same both in classroom and instructor led live online fully interactive mode.

How do I attend the online classes? Are they interactive or self-paced?

We provide both the options and for instructor led live online classes we use the gold standard platform used by the top universities across the globe. These video sessions are fully interactive and students can chat or even ask their questions verbally over the VoIP in real time to get their doubts cleared.

What do I need to attend the online classes?

To attend the online classes, all you need is a laptop/PC with a basic internet connection. Students have often shared good feedback of attending these live classes through their data card or even their mobile 3G connection, though we recommend a basic broadband connection.

For best user experience, a mic-headphone is recommended to enhance the voice quality, though the laptop’s in-built mic works fine and you can ask your question over the chat as well.

How can I reach out to someone if I have doubts post class?

Through the LMS, students can always connect with the trainer or even schedule one-to-one time over the phone or online. During the course we also schedule periodic doubts-clearing classes though students can also ask doubts of a class in the subsequent class.

LMS also has a discussion forum where a lot of your doubts might get easily answered.

Incase you are having a problem still, repeat the class and schedule one-to-one time with the trainer.

What is your refund policy?

Instructor Led Live online or Classroom - Within 7 days of registartion date and latest 3 days before batch start
Video-based - 2 days

Can I pay in installments?

Yes. While making the fee payment, most of the courses have the installment option.

I am having difficulty coping up with my classes. What can I do?

For all the courses, we also provide the recordings of each class for their self-reference as well as revision in case you miss any concept in the class. In case you still have doubts after revising through the recordings, you can also take one-to-one time with the faculty outside classes during. Furthermore, if students want to break their courses in different modules, they get one year time to repeat any of the classes with other batches.

What are the system requirements for the software?

There is no particular system requirement for this course since the tools required for this course (Excel, SAS and R) can easily be installed on almost every laptop with basic configuration available these days. However, if possible, it is recommended to have 64-bit operating system.

“

Well a group of seasoned data science professionals are always ready 24*7 to help/guide/mentor you. They have a very neatly prepared reference material, in classes apart from curriculum they regularly shared their real time experiences which they faced while they were into corporate and always updated with latest changes and trends in analytics industry. I strongly recommend AnalytixLab to everyone thinking of learning Data Science.

- Dheeraj Kumar Gugnani (Senior Consultant at Capgemini)

Have Questions?
Contact us and we shall
get back with answers.

Course Duration	306 hours
Classes	36
Tools	Excel, SAS, R
Learning Mode	Live/Video Based
Next Batch	07th July, 2018 (Gurgaon)

SAS Data Science Training - Data Science using SAS & R

Industry relevant SAS Data Science training with strong focus of machine learning as well.