Data science and machine learning courses online
Skill-Lync teaches data science in 13 online courses: ten 12-week courses on statistics, the maths of machine learning, ML algorithms, deep learning, SQL, Excel, Tableau and Power BI, and three programs that bundle them with career services. Here they all are with fees, hours and projects, which ones overlap, and which fits the job you want.
As of 20 Nov 2026: 13 courses · ₹40,000 to ₹2,75,000 · Fees are the list price on each course page, inclusive of all charges
Every Skill-Lync course that teaches Data Science
Projects is the number of industry projects listed on the course page. Programs also include the courses' smaller assignments. EMI figures are the lowest monthly plan shown on the course page.
Which one should you pick?
- You want to understand machine learning, not just call a library. Start with Math behind Machine Learning & AI (12 weeks, ₹40,000, 25 h): statistics, likelihood, gradient descent, linear algebra and back-propagation, each tied to the algorithm that uses it. Then take Introduction to Machine Learning Algorithms in Python (40 h, the longest course here), which goes from Python libraries through regression, PCA, trees, random forests and clustering to a first neural network.
- You only want one machine learning course. Take Introduction to Machine Learning Algorithms (40 h) rather than Machine Learning Fundamentals In Depth (15 h). They cover the same ground (regression, classification, random forests, k-means, hierarchical clustering, PCA); the first has more than twice the video and also teaches the Python libraries. Both sit inside the two PG programs.
- You want deep learning. Advanced Deep Learning using Python (12 weeks, ₹40,000, 22 h) starts at neural networks, so take a machine learning course first. It runs from back-propagation, regularisation and optimisers to CNNs, RNNs and NLP basics, in TensorFlow 2. For vision-specific work see the computer vision courses.
- You want a data analyst job. SQL for Data Science (22 h) first, then one dashboard tool: Tableau (24 h) or Power BI. Of the two Power BI courses, Business Intelligence using Power BI (23 h) goes further (M language, publishing) than Effective Dashboards using Power BI (7 h); buy one, not both. Excel (24 h, pivots to VBA) is worth it if your target employers run on spreadsheets.
- You want a program with career services. Three bundles. Pre-Graduate Program in Data Analytics and Data Science (16 weeks, ₹1,50,000): Core Python, SQL, Statistics and Tableau. PG Program in Data Science and Machine Learning (24 weeks, ₹2,75,000, EMI from ₹14,375 a month): Core Python, Statistics, both ML courses, Advanced Deep Learning and SQL. PG Program in Data Analytics and Data Science (24 weeks, ₹2,75,000): nine courses, the DSML six plus Excel, Tableau and Effective Dashboards using Power BI.
What is Data Science?
Data science is answering questions with data: cleaning a messy table, summarising it, testing whether a difference is real, and building a model that predicts something new. Machine learning is the modelling part, where the computer fits the rule from examples instead of you writing it. Data analytics is the reporting part: SQL queries, spreadsheets and dashboards that tell a manager what happened last month.
Most jobs use a short chain of tools. SQL pulls the data out of a database. Python with pandas and NumPy cleans and reshapes it. Statistics says whether a pattern is signal or noise. Scikit-learn style algorithms (regression, decision trees, random forests, k-means) fit models, and deep learning (neural networks) takes over for images, text and very large datasets. Excel, Tableau or Power BI show the result to people who will never open a notebook.
Here is why accuracy alone can fool you. A plant screens 1,000 machines, and 50 of them really have a bearing fault. A model flags 60: 40 of them are truly faulty (true positives) and 20 are healthy (false alarms); it misses 10 faulty machines. Its accuracy is (40 + 930) ÷ 1,000 = 97%. A "model" that calls every machine healthy scores 95% and catches nothing.
So data scientists look at precision and recall. Precision = 40 ÷ (40 + 20) = 0.667: two in three alarms are real. Recall = 40 ÷ (40 + 10) = 0.8: it finds 80% of the faults. F1, the harmonic mean of the two, is 0.727. Whether a false alarm or a missed fault costs more decides which number you push up; on rare-event data like this, accuracy is the number to ignore.
Regression is the other everyday tool, and engineers already know it as a line of best fit. A spring test records extension at five loads: 1 to 5 kN gave 2.1, 3.9, 6.2, 7.8 and 10.1 mm. Least squares picks the line that makes the squared misses smallest: slope = Σ(x − x̄)(y − ȳ) ÷ Σ(x − x̄)² = 19.9 ÷ 10 = 1.99 mm per kN, intercept = 6.02 − 1.99 × 3 = 0.05 mm. That is a stiffness of about 503 N/mm.
The line explains R² = 0.9973 of the variation in the readings, and it predicts 11.99 mm at 6 kN. That last number is a guess outside the tested range: if the spring starts to yield at 5.5 kN, the model will not know. Machine learning is this idea scaled up to many inputs and curved models, with the same two habits: check the fit on data the model has not seen, and do not trust it beyond the data.
What a Data Science course covers
- Statistics and probability. Probability and set theory, discrete and continuous distributions, inferential statistics, hypothesis tests and non-parametric tests (the Statistics course); likelihood, gradient descent, linear algebra for PCA, derivatives and back-propagation (the Math behind ML course).
- Machine learning algorithms. Cross-validation and the bias-variance trade-off, evaluation metrics, linear and multivariate regression, PCA, logistic regression, k-nearest neighbours, decision trees and random forests, k-means and hierarchical clustering, a first neural network.
- Deep learning. Feed-forward networks, activation functions, model evaluation and regularisation, optimisers, CNNs (two weeks), RNNs and LSTMs (two weeks), the basics of NLP and the steps of an end-to-end ML project, in Python and TensorFlow.
- SQL and databases. Creating and changing MySQL databases, SELECT queries, joins across tables, data exploration, indexes, views and transactions, stored procedures, and running SQL from Excel and from Python.
- Dashboards and reporting. Excel pivot tables, lookups, Power Query, PowerPivot, macros and VBA; Tableau shelves, table calculations, joins and blending, LOD expressions and dashboards; Power BI data models, DAX, the query editor, M language, interactive reports and publishing.
The courses in detail
Data Analysis and Visualization using Excel
Excel for analysis: functions, formatting and templates, conditional and lookup functions, pivot tables, Power Query and PowerPivot, large data sets, macros, VBA and email automation.
Projects include: Data Cleaning and Transformation using Pivot Table and Charts; Report Creation using PowerQuery, Macro VBA, List functions, and Data Validation Functions.
Tools: MS Excel
Data Analysis and Visualization with Tableau
Tableau from shelves and cards to dashboards: sorting, grouping, filters and table calculations, joins, blending and relationships, parameters and set actions, nested LODs and mapping, publishing.
Projects include: Developing a Dashboard on Tableau - Women in STEM Fields; Developing a Dashboard on Tableau - Literacy Rate in Tamilnadu.
Tools: Tableau
SQL for Data Science
MySQL for analysis: creating and changing databases, SELECT queries, joins across tables, data exploration, indexes, views and transactions, stored procedures, and SQL from Excel and Python.
Projects include: C2C E-Commerce User’s Behaviour Analysis; Analyzing the choice of career for the Alumni of Engineering College..
Tools: MySQL, Python, Anaconda
Statistics and Probability for Data Sciences
Probability and statistics for data work in Jupyter: set theory, probability, discrete and continuous distributions, inferential statistics, hypothesis tests and non-parametric tests. Two projects on medical-insurance and fermented-drink data.
Projects include: Analysis of Medical Insurance Data; Analysis of Fermented Drink Data.
Tools: Jupyter Notebook
Advanced Deep Learning using Python
Neural networks from the maths up in Python and TensorFlow: activations, back-propagation, regularisation, ensembles and optimisers, then CNNs (two weeks: convolution, padding, pooling, transfer learning), RNNs and LSTMs, and basic NLP with word2vec.
Projects include: Logistic Regression and Gradient Descent; ANN, CNN and RNN.
Tools: Python
Business Intelligence using Power BI
Power BI in 23 h: data sources and formatting, visuals, filters and calculated fields, DAX from basics to advanced, dashboards and reports, Power Query and M, publishing and sharing. Projects use cyber-security data.
Projects include: Analysis of Reported CVEs Pattern; Behavioral Analysis of Android Ransomware Attacks.
Tools: Power BI
Effective Dashboards using Power BI
A short (7 h) Power BI course: query editor transforms, the relational data model, DAX basics and advanced functions, and interactive reports. Projects on supply-demand gaps and COVID-19 vaccination trends.
Projects include: Supply and Demand Gap Analysis; COVID-19 Vaccinations Trend Analysis.
Tools: Power BI
Introduction to Machine Learning Algorithms and their Implementation in Python
ML algorithms in Python, 40 h: Python libraries, cross-validation and bias-variance, metrics, linear and multivariate regression, PCA, logistic regression and kNN, decision trees and random forests, k-means and hierarchical clustering, neural networks.
Projects include: Stock Market Data Analysis and Visualization; Developing an Early Warning System with Given Data.
Tools: Python
Machine Learning Fundamentals In Depth
A shorter (15 h) pass over core ML in Python: probability basics, supervised prediction and classification, random forests and model evaluation, k-means, hierarchical clustering and PCA. Two projects: regression analysis and k-means.
Projects include: Descriptive Analysis and Regression Analysis; K-Means Clustering.
Tools: Python
Math behind Machine Learning & Artificial Intelligence using Python
The maths under ML, each topic tied to its algorithm: combinatorics, statistics and probability, likelihood for logistic regression, gradient descent, linear algebra for PCA, derivatives and back-propagation, then Python.
Projects include: Logistic regression; Gradient descent.
Tools: Python
Pre-Graduate Program in Data Analytics and Data Science
Four courses in 16 weeks: Core and Advanced Python, SQL for Data Science, Statistics and Probability, and Tableau, with 8 projects and career services.
Projects include: English Dictionary App; Library Book Management System; C2C E-Commerce User’s Behaviour Analysis; Analyzing the choice of career for the Alumni of Engineering College..
Tools: MySQL, Python, Anaconda, Tableau, SQLite, Jupyter Notebook
Post Graduate Program in Data Analytics and Data Science
Nine courses in 24 weeks: Core and Advanced Python, SQL for Data Science, Tableau, Excel, Statistics and Probability, both machine learning courses, Advanced Deep Learning and Effective Dashboards using Power BI, with 18 projects.
Projects include: English Dictionary App; Library Book Management System; C2C E-Commerce User’s Behaviour Analysis; Analyzing the choice of career for the Alumni of Engineering College..
Tools: Python, MySQL, Anaconda, Tableau, SQLite, MS Excel, Power BI, Jupyter Notebook
Post Graduate Program in Data Science and Machine Learning
Six courses in 24 weeks: Core and Advanced Python, Statistics and Probability, both machine learning courses, Advanced Deep Learning and SQL, with 12 projects and career services.
Projects include: English Dictionary App; Library Book Management System; Analysis of Medical Insurance Data; Analysis of Fermented Drink Data.
Tools: Python, MySQL, Anaconda, SQLite, Jupyter Notebook
Jobs after a Data Science course
Typical job titles: data analyst, MIS or reporting analyst, business analyst, BI developer (Power BI or Tableau), data scientist, machine learning engineer, and research analyst at market-research firms. Entry roles are mostly analyst roles built on SQL, Excel and a dashboard tool; data scientist and ML engineer roles usually ask for stronger statistics, Python and a portfolio, and often a few years of analyst experience first.
From Skill-Lync's own placement records (as of 20 Nov 2026, 3,905 placements across all programs): the PG Program in Data Analytics and Data Science has 178 placement records from 2022 to 2025, 160 with a salary: median 3.6 LPA. 86 of the 178 have "analyst" or "analysis" in the job title or role; the most frequent employer is NielsenIQ (14 records). The PG Program in Data Science and Machine Learning has only 4 records (2022 to 2023), too few for a median.
By job title across all programs: 52 placements are titled data analyst (48 with a salary: median 3.75 LPA, range 1.5 to 5.25 LPA; 47 of them from the PG data analytics program). 15 have data science or machine learning titles (13 with a salary: median 4.5 LPA, range 1.8 to 10 LPA, 2022 to 2024). These are learners who told us they were placed, so treat them as a starting point, not as today's market rate. Salary data by field: salaries.
Free Data Science tutorials
Start here before you pay for anything. These are written by Skill-Lync learners and engineers:
- What is Data Science ?
- What Is Machine Learning? A Worked Example and How to Get Started
- Machine Learning Syllabus: A Brief Overview
- How to Self-Study Data Science: 7 Tips and a 24-Week Plan
- Data Science Vs Data Analytics - What Is Better?
- Descriptive Vs Inferential Statistics - What is the Difference?
- Confusion Matrix in Machine Learning
- K-Nearest Neighbor Algorithm in Machine Learning
- Top Ensemble Techniques in Machine Learning
- Deep Learning with Python: A Comprehensive Guide for Beginners
- The Pandas Cheat Sheet You Should Know
- Importance of SQL in Data Science: Unlocking the Power of Relational Databases
- Exploring the Differences: Power BI vs. Tableau for Data Visualization
- Machine Learning for Mechanical Engineers: Skills, Example and Projects
- Most Frequently Asked Interview Questions for Data Scientists
Before you pay
Most of our data placements are analyst jobs, not data scientist jobs. Plan for an analyst first role (SQL, Excel, dashboards) and move to modelling with experience and a portfolio. Ask the counsellor for recent placements in the exact role you want before you pay. Ignore generic salary ranges for data scientists; our own median for the PG data program is 3.6 LPA.
The PG DSML costs more than its parts. Its six courses bought one by one come to ₹2,40,000, against ₹2,75,000 for the program (the program's hours, 151, are exactly the six courses' hours). What the program adds is career services: its pricing lists career service assurance and career mentorship, which the short courses do not. The Pre-Graduate program (₹1,50,000) costs less than its four courses (₹1,60,000); the PG data analytics program (₹2,75,000) much less than its nine (₹3,60,000).
Do not buy overlapping courses. The two machine learning courses cover the same algorithms; the two Power BI courses cover the same tool. Statistics and Math behind ML overlap on probability and statistics. If you buy a program, do not also buy the short courses inside it.
Some hours are thin. Effective Dashboards using Power BI is 7 hours over 12 weeks; Machine Learning Fundamentals In Depth is 15. The Statistics course lists ten weekly topics in its 12 weeks. Hours are recorded video; you will need as much time again for practice and projects.
Check the project data matches your goal. Business Intelligence using Power BI builds its two projects on cyber-security data (reported CVEs and Android ransomware). Fine for learning Power BI, less relevant if you want to show a sales or operations dashboard.
Data Science course FAQs
What is the fee for a data science course at Skill-Lync?
As of 20 Nov 2026: each of the ten short courses (statistics, ML, deep learning, SQL, Excel, Tableau, Power BI) is ₹40,000. The Pre-Graduate Program in Data Analytics and Data Science is ₹1,50,000 (EMI from ₹7,841 a month); the PG Program in Data Science and Machine Learning and the PG Program in Data Analytics and Data Science are ₹2,75,000 each (EMI from ₹14,375).
What is the syllabus of a machine learning course?
A typical machine learning syllabus runs: Python and its libraries, statistics and probability, data cleaning, regression, classification (logistic regression, k-nearest neighbours, decision trees, random forests), evaluation metrics and cross-validation, clustering and PCA, then neural networks. Skill-Lync's Introduction to Machine Learning Algorithms course follows that order over 12 weeks.
How long does it take to learn data science?
Each Skill-Lync short course runs 12 weeks with 7 to 40 hours of video. The programs run 16 weeks (Pre-Graduate, 98 h) or 24 weeks (PG, 151 and 207 h). Being job-ready as an analyst usually takes SQL, one dashboard tool and two or three projects; modelling roles take longer.
Do I need maths or coding before a data science course?
You need school-level maths (algebra, a little probability) and comfort with a computer; the PG DSML page asks for basic mathematics and no other prerequisite. All three programs start with Core and Advanced Python Programming, so you can begin without coding. For a single ML course, learn basic Python first.
What is the difference between data science and data analytics?
Data analytics describes what happened: SQL queries, spreadsheets and dashboards for business decisions. Data science also predicts and explains: statistics, machine learning models and experiments. Analytics is the more common entry job; data science roles usually expect stronger statistics and Python.
Can mechanical or electrical engineers learn machine learning?
Yes. Regression, classification and clustering apply directly to sensor data, test results and maintenance logs: predicting tool wear, spotting bearing faults, fitting material curves. Start with statistics and one ML course in Python; Skill-Lync's AI for mechanical engineers projects show worked examples on public engineering datasets.