Almost all official and personal activities in todays’ world are now intermediated by digital data or generate digital trail either intentionally or otherwise. As the Internet of Things (IoT) becomes mainstream and ubiquitous, the need for scientists who understand data in all its aspects will continue to grow strongly. A graduate of any field (especially those with significant quantitative content) without ability to make sense out of digital data may perceive him/herself as an educated illiterate because understanding the fundamentals of data science has become essential for functioning as an informed citizen. Data science is concerned with the acquisition, storage, retrieval, processing and conversion of data into knowledge where the quantum of data is very large. ABS is taking leadership in providing training services in this knowledge of the future by launching Certificate in Data Science.
Purpose: The purpose of the Certificate in Data Science is to provide entry-level skilled professionals that would support qualified professionals in related job roles. Students shall be introduced to relevant data science tools that can help them to pursue a professional career in data science. The curriculum is designed to build capacity in business data collection, cleaning, and munging using knowledge of statistics, mathematics, business metrics and computer science.
The objectives of the programme are to:
- Become recognised as one of the leading business schools that build capacity in data science knowledge domain.
- Produce manpower that can support organisations in taking advantage of structured and unstructured data for profitability.
- Produce young entrepreneurs that can provide data support to organisations by devising and applying models/algorithms to mine the stores of big data
The programme is proposed for 6 Months. Two semesters of 3 month per semester.
Mode of Study
The programme will run on a flexible full time basis.
Requirements for Admission
5 O’L Credit passes with at least a Pass in English Language and a Credit in General Mathematics. Basic computer skills (opening files, folders, and applications, copying and pasting); Access to personal or home computer for practice. Experienced/matured candidates that demonstrate sufficient background knowledge by passing entrance examination and interview may also be considered for admission.
1ST SEMESTER (3 MONTHS)
|1.||CDS 101||Nature of Data Science||2|
|2||CDS 103||Data Visualization||2|
|3||CDS 105||Analytic Toolbox||2|
|4||CDS 107||Python 1||2|
|6||CDS 111||Machine Learning||2|
2nd SEMESTERS (3 MONTHS)
|1.||CDS 102||Geospatial Analysis||2|
|2||CDS 104||Deep Learning||2|
|3||CDS 106||Feature Engineering||2|
|4||CDS 108||Python 2||2|
|5||CDS 199||Practical Project||4|
CDS 101: Nature of Data Science
Introduction to data science; Evolution and development of data science; Business Intelligence versus Data Science; Prerequisites for Data Science. Semantics and metadata; cyberinfrastructure and cloud computing; security and privacy.
CDS 103: Data Visualization I
The importance of data visualization; anatomy of an Excel chart; Most common data types; When to use a clustered column chart. Introduction to coding for data visualization; Seaborn package.
CDS 105: Analytic Toolbox
Excel for form creation and Pivot Table; Excel VBA; Business Intelligence tools for data analysis; Tableau for Pivot Table and Pivot Chart; Power BI for business model and data analysis; Fine Report for self-service data decision analysis and report; R and Python for professional statistical analysis.
CDS 107: Python 1
A quick introduction to Python syntax, variable assignment, and numbers; Functions and Getting Help. Python data types; Imports, operator overloading, and survival tips for venturing into the world of external libraries. Working with Panda.
CDS 109: SQL
Getting Started with SQL and Big Query; Learn the workflow for handling big datasets with Big Query and SQL; Select, From & Where; The foundational components for all SQL queries. Joining Data and Combine data sources.
CDS 111: Machine Learning
How Models Work; Basic Data Exploration; Load and understand your data; Building Machine Learning Model; Model Validation; Measure the performance of the model; Test and compare alternatives; Under-fitting and Overfitting; Fine-tune model for better performance; Random Forests.
CDS 102: Geospatial Analysis
Get started with plotting in GeoPandas; Coordinate Reference Systems; Representing the Earth’s surface in 2 dimensions; Making interactive heatmaps and choropleth maps; Manipulating Geospatial Data; Joining data based on spatial relationships; Proximity Analysis.
CDS 104: Deep Learning
Intro to Deep Learning for Computer Vision; A quick overview of how models work on images; Building Models from Convolutions. Introduction to code writing Dropout and Strides for Larger Models.
CDS 106: Feature Engineering
Baseline Model; Categorical Encodings; Different ways to encode categorical data for modeling; Feature Generation; Combining data from multiple rows into useful features; Feature Selection; Getting the best set of features for your model.
CDS 108: Python 2
Run and edit python scripts; Interact with raw input from users; Identify and handle errors and exceptions in your code; Open, read, and write to files; multidimensional NumPy arrays (ndarrays); Create, access, and modify the main objects in Pandas, Series and DataFrames.
CDS 199: Practical Project
The project would be based on or model in line with a global data science challenge problem. Open problem and practical datasets.
Scoring and Grading System
The marks obtained shall be converted into letter grades and transformed to grade points as follows:-
|Distinction (A)||70 % and Above|
|Credit (B)||60% – 69%|
|Pass (C)||50% – 59.9%|
|Fail (F)||49.9% and Below|
Thus, to obtain a pass grade in a course, a student must score at least 50%