Advanced Data Science

This Data Science course using Python and R endorses the CRISP-DM Project Management methodology and contains a preliminary introduction of the same. Data Science is a 90% statistical analysis and it is only fair that the premier modules should bear an introduction to Statistical Data Business Intelligence and Data Visualization techniques. Students will grapple with Plots, Inferential Statistics, and various Probability Distributions in the module. A brief exposition on Exploratory Data Analysis/ Descriptive Analytics is huddled in between. The core modules commence with a focus on Hypothesis Testing and the "4" must know hypothesis tests. Data Mining with Supervised Learning and the use of Linear Regression and OLS to enable the same find mention in succeeding modules. The prominent use of Multiple Linear Regression to build Prediction Models is elaborated. The theory behind Lasso and Ridge Regressions, Logistic Regression, Multinomial Regression, and Advanced Regression For Count Data is discussed in the subsequent modules.

A separate module is devoted to Data Mining Unsupervised Learning where the techniques of Clustering, Dimension Reduction, and Association Rules are elaborated. The nitty-gritty of Recommendation Engines and Network Analytics are detailed in the following modules. The various Machine Learning algorithms follow next like k-NN Classifier, Decision Tree and Random Forest, Ensemble Techniques, Bagging and Boosting, Adaboost, and Extreme Gradient Boosting. Text Mining, Natural Language Processing, Naive Bayes, Perceptron, and Multilayer Perceptron are the focal points of the succeeding modules.

The fundamentals of Neural Network ANN and Deep Learning Black Box Techniques like CNN, RNN, and SVM find prominent features as well. The concluding modules contain model-driven and data-driven algorithms for Forecasting and Time Series Analysis.

What is Data Science?

Data science is an amalgam of methods derived from statistics, Data Analytics, and Machine Learning that are trained to extract and analyze huge volumes of structured and unstructured data.

Who is a Data Scientist?

A Data Scientist is a researcher who has to prepare huge volumes of big data for analysis, build complex quantitative algorithms to organize and synthesize the information, and present the findings with compelling visualizations to senior management.

A Data Scientist enhances business decision making by introducing greater speed and better direction to the entire process.

A Data Scientist must be a person who loves playing with numbers and figures. A strong analytical mindset coupled with strong industrial knowledge is the skill set most desired in a data scientist. He must possess above the average communication skills and must be adept in communicating the technical concepts to non - technical people. Data Scientists need a strong foundation in Statistics, Mathematics, Linear Algebra, Computer Programming, Data Warehousing, Mining, and modeling to build winning algorithms.

They must be proficient in tools such as Python, R, R Studio, Hadoop, MapReduce, Apache Spark, Apache Pig, Java, NoSQL database, Cloud Computing, Tableau, and SAS.