Professional skills
Data Science and Machine Learning Bootcamp in China
Showing starts assigned to China. Change country or city · Global course
Ten-day, 80-hour bootcamp to build Python, statistics and machine learning skills through projects on real data with daily exam-style drills.
THE BIG PICTURE
About this course
This bootcamp aligns to the AWS Certified Machine Learning – Specialty credential, awarded by Amazon Web Services (AWS), for practitioners who design, build, deploy and maintain machine learning solutions. Across ten days you will work through Python, data wrangling, statistics, exploratory analysis, feature engineering, supervised and unsupervised learning, deep learning, and MLOps. You will complete structured labs and a portfolio project using pandas, scikit-learn and TensorFlow, with practical exercises on AWS services including SageMaker for training and deployment. The AWS Certified Machine Learning – Specialty exam comprises 65 questions (multiple-choice and multiple-response) in 170 minutes, closed book, delivered at test centres or online proctored via Pearson VUE or PSI. A scaled score of 750 (on a 100–1000 scale) is required to pass, and the certification is valid for three years. Amazon Web Services (AWS) owns the certification scheme. MindClick provides training and exam preparation and is not an accredited or authorised partner.
What you’ll learn
- Write clean, reproducible Python and pandas code for data ingestion, cleaning and transformation
- Perform exploratory data analysis and communicate findings using clear visualisations and statistical tests
- Engineer features, address missing data and class imbalance, and build preprocessing pipelines
- Train, tune and evaluate supervised models and interpret results with appropriate metrics
- Apply unsupervised learning and dimensionality reduction to discover structure in data
- Build and train deep learning models with TensorFlow/Keras for images and sequences
- Package, deploy and monitor models using REST APIs and AWS services such as S3 and SageMaker
- Practise exam-style questions and complete a timed mock to prepare for the AWS ML – Specialty exam
A CLEAR PATH FORWARD
10-day course agenda
10 instructor-led days (80 contact hours) mapped to the exam domains. Each day combines short concept sessions, hands-on practice on a running case study and exam-style questions.
- Learning route
- 10 recommended days
- Practical work
- 10 guided activities
- Finish with
- Mock exam + certification exam
Take a look at each day. Open a section to see the topics and practical work.
Day 1Python and Data FoundationsData Engineering and Exploratory Data Analysis
What we’ll cover
- 09:00–10:30 · Orientation, workflow, environment setup (Anaconda, Jupyter, VS Code), Python refresh
- 10:45–12:15 · Data ingestion with pandas: CSV/Parquet, SQL, APIs; schema and typing
- 13:15–14:45 · Cleaning and transforming data: missing values, joins, tidy data
- 15:00–16:00 · Efficient pandas: vectorisation, memory use, pipelines
- 16:00–16:30 · Visualisation basics with Matplotlib and Seaborn
- 16:30–17:00 · Exam-style practice questions: Data Engineering and EDA fundamentals
- 17:00–17:30 · Lab debrief and Q&A
Put it into practice
Build a data wrangling notebook that ingests raw CSVs, cleans anomalies, joins reference data and produces an analysis-ready dataset. Commit the notebook and outputs to a Git repository.
You’ll take away
Reusable data cleaning notebook and processed dataset
Day 2Statistics for Data ScienceExploratory Data Analysis
What we’ll cover
- 09:00–09:30 · Recap of Day 1 and quick knowledge check
- 09:30–10:30 · Descriptive statistics, distributions and sampling
- 10:45–12:15 · Confidence intervals and hypothesis testing
- 13:15–14:45 · Correlation, covariance and feature relationships
- 15:00–16:00 · Visual storytelling: choosing effective plots
- 16:00–16:30 · Lab: EDA report with ydata-profiling and Seaborn
- 16:30–17:00 · Exam-style practice questions: EDA and statistics
- 17:00–17:30 · Daily review and parking lot
Put it into practice
Produce an EDA report for a real dataset, including statistical tests and clear visualisations. Summarise insights and risks for a non-technical audience.
You’ll take away
EDA report with visuals and executive summary
Day 3Feature Engineering and Data PreparationData Engineering and Modelling
What we’ll cover
- 09:00–09:30 · Recap of Day 2 and outline for pipelines
- 09:30–10:30 · Handling missing data, outliers and scaling
- 10:45–12:15 · Encoding categoricals, target leakage and data leakage controls
- 13:15–14:45 · Feature generation and selection; imbalance strategies
- 15:00–16:00 · scikit-learn pipelines and ColumnTransformer
- 16:00–16:30 · Lab: end-to-end preprocessing pipeline
- 16:30–17:00 · Exam-style practice questions: data prep and leakage
- 17:00–17:30 · Daily review and Q&A
Put it into practice
Create a robust preprocessing pipeline for a tabular dataset, including scaling, encoding and imbalanced learning. Validate with train/validation splits to prevent leakage.
You’ll take away
Versioned preprocessing pipeline ready for reuse
Day 4Supervised Learning I: Regression and ClassificationModelling
What we’ll cover
- 09:00–09:30 · Recap of Day 3 and metric selection
- 09:30–10:30 · Linear and logistic regression: assumptions and regularisation
- 10:45–12:15 · Tree-based models: decision trees and random forests
- 13:15–14:45 · Gradient boosting (XGBoost/LightGBM) concepts and tuning
- 15:00–16:00 · Cross-validation, bias–variance and learning curves
- 16:00–16:30 · Lab: baseline vs tuned models comparison
- 16:30–17:00 · Exam-style practice questions: supervised learning
- 17:00–17:30 · Daily review and troubleshooting
Put it into practice
Train baseline and tuned models for a binary classification problem, comparing metrics and learning curves. Document trade-offs and chosen metric.
You’ll take away
Model comparison notebook with evaluation summary
Day 5Model Evaluation and ExperimentationModelling
What we’ll cover
- 09:00–09:30 · Recap of Day 4 and experiment tracking
- 09:30–10:30 · Evaluation metrics: regression and classification (ROC, PR, AUC)
- 10:45–12:15 · Hyperparameter tuning: GridSearchCV, RandomizedSearchCV and Optuna
- 13:15–14:45 · Interpretability: feature importance, SHAP basics
- 15:00–16:00 · Reproducibility: seeds, data splits and documentation
- 16:00–16:30 · Lab: tracked experiments with MLflow
- 16:30–17:00 · Exam-style practice questions: evaluation and tuning
- 17:00–17:30 · Daily review and next steps
Put it into practice
Run multiple experiments tracked with MLflow, tuning a model and explaining predictions with SHAP. Export artefacts and metrics for peer review.
You’ll take away
Tracked experiment runs with metrics and artefacts
Day 6Unsupervised Learning and Dimensionality ReductionModelling and Exploratory Data Analysis
What we’ll cover
- 09:00–09:30 · Recap of Day 5 and unsupervised goals
- 09:30–10:30 · Clustering: k-means, hierarchical, DBSCAN
- 10:45–12:15 · Dimensionality reduction: PCA and t-SNE/UMAP for exploration
- 13:15–14:45 · Anomaly detection approaches
- 15:00–16:00 · Validating clusters and stability checks
- 16:00–16:30 · Lab: customer segmentation workflow
- 16:30–17:00 · Exam-style practice questions: unsupervised methods
- 17:00–17:30 · Daily review and retrospectives
Put it into practice
Build a customer segmentation using clustering and PCA, validate segment quality and profile segments. Present actionable segment descriptors.
You’ll take away
Segmentation analysis with profiles and visuals
Day 7Deep Learning with TensorFlow/KerasModelling
What we’ll cover
- 09:00–09:30 · Recap of Day 6 and DL concepts
- 09:30–10:30 · Neural network fundamentals and Keras API
- 10:45–12:15 · CNNs for images: architecture, augmentation and regularisation
- 13:15–14:45 · Sequence models: RNNs/LSTMs and simple Transformers
- 15:00–16:00 · Training at scale: GPUs, callbacks and early stopping
- 16:00–16:30 · Lab: image classification pipeline
- 16:30–17:00 · Exam-style practice questions: deep learning
- 17:00–17:30 · Daily review and lab clinic
Put it into practice
Implement an image classifier with TensorFlow/Keras, applying augmentation and callbacks to improve validation performance. Save the best model and evaluate on a hold-out set.
You’ll take away
Trained Keras model and evaluation report
Day 8MLOps: Packaging, Deployment and MonitoringMachine Learning Implementation and Operations
What we’ll cover
- 09:00–09:30 · Recap of Day 7 and deployment options
- 09:30–10:30 · Model packaging: Conda/virtualenv, Docker fundamentals
- 10:45–12:15 · Serving models as REST APIs (FastAPI) and testing
- 13:15–14:45 · Monitoring: performance, drift and data quality checks
- 15:00–16:00 · Responsible AI: bias detection and mitigation
- 16:00–16:30 · Lab: containerised inference service
- 16:30–17:00 · Exam-style practice questions: implementation and ops
- 17:00–17:30 · Daily review and support
Put it into practice
Containerise a trained model and expose a FastAPI endpoint with basic logging and health checks. Measure latency and implement a simple drift alert.
You’ll take away
Dockerised inference service with monitoring hooks
Day 9AWS SageMaker for Training and DeploymentAll domains with emphasis on Implementation and Operations
What we’ll cover
- 09:00–09:30 · Recap of Day 8 and AWS basics (IAM, S3, regions)
- 09:30–10:30 · SageMaker Studio/Notebooks and data preparation in S3
- 10:45–12:15 · Managed training jobs and built-in algorithms
- 13:15–14:45 · Hyperparameter tuning jobs and estimators
- 15:00–16:00 · Deployment: real-time endpoints, batch transform and autoscaling
- 16:00–16:30 · Monitoring: Model Monitor, CloudWatch and logs
- 16:30–17:00 · Exam-style practice questions: AWS ML workflows
- 17:00–17:30 · Daily review and readiness check
Put it into practice
Use SageMaker to train a model on data in S3, tune key hyperparameters and deploy to a real-time endpoint. Validate predictions and review logs and metrics.
You’ll take away
SageMaker project with training, tuning and endpoint
Day 10Capstone, Exam Readiness and Next StepsAll domains
What we’ll cover
- 09:00–09:30 · Recap of Day 9 and capstone goals
- 09:30–10:30 · Capstone build: define problem, metric and baseline
- 10:45–12:15 · Capstone build: modelling and evaluation
- 13:15–14:45 · Capstone build: packaging and deployment checklist
- 15:00–16:30 · Timed mock exam (AWS ML – Specialty style)
- 16:30–17:00 · Mock exam review and targeted revision plan
- 17:00–17:30 · Exam booking guidance, test-day tips and course wrap-up
Put it into practice
Complete a capstone that integrates data prep, modelling and deployment, then sit a timed mock exam. Use the review to finalise a study and booking plan.
You’ll take away
Capstone project and personalised exam study plan
Bring it all together
Certification exam: AWS Certified Machine Learning – Specialty (MLS-C02), awarded by Amazon Web Services (AWS). 65 questions (multiple-choice and multiple-response), 170 minutes, closed book, Test centre or online proctored via Pearson VUE or PSI. Pass mark: Scaled score of 750 (100–1000 scale). Validity: 3 years from date earned. Every attendee also receives a MindClick certificate of completion for 80 contact hours.
What you receive
You earn two separate credentials. The sample shows the MindClick training certificate.
- MindClick certificate of completion: 10 days, 80 contact hours, issued to every attendee who completes the course.
- AWS Certified Machine Learning – Specialty (MLS-C02): issued by Amazon Web Services (AWS) when you meet its requirements and pass the exam.
Before you choose your learning route
Session timings are indicative; the trainer may adjust them for the group. Exam details reflect the awarding body’s published information at the time of writing; confirm the current version when you book.
Amazon Web Services (AWS) owns this certification scheme. MindClick provides training and exam preparation and is not an accredited or authorised partner of Amazon Web Services (AWS).
Fees
| Delivery format | Fee per learner | Exam fee |
|---|---|---|
| Live online | $2,800 USD | Included |
| Classroom | $4,500 USD | Included |
One awarding-body certification exam attempt is included in the training fee. Confirm the current fee, any applicable tax and what the fee covers in writing before you pay.
Prerequisites
- There are no formal prerequisites from AWS. Recommended: solid Python, basic statistics, and 1–2 years working with ML or data workflows; familiarity with AWS helps. Bring a laptop with admin rights, modern browser, Python 3.10+ (Anaconda/Miniconda), and a GitHub account.
FIND YOUR START
Confirmed batch starts
Choose a published start, then review your offer in the same enrollment flow. A start date is not the full timetable or a seat reservation.
Choose your country & monthStarts
- Training location
- Shanghai, China
- Local timezone
- Asia/Shanghai
Joining details and full session timetable to be supplied.
Starts
- Training location
- Shanghai, China
- Local timezone
- Asia/Shanghai
Joining details and full session timetable to be supplied.
Starts
- Training location
- Shanghai, China
- Local timezone
- Asia/Shanghai
Venue and full session timetable to be supplied.
Starts
- Training location
- Shanghai, China
- Local timezone
- Asia/Shanghai
Venue and full session timetable to be supplied.
Starts
- Training location
- Shanghai, China
- Local timezone
- Asia/Shanghai
Joining details and full session timetable to be supplied.
Frequently asked questions
How long is the course?
10 days, 80 contact hours, normally 09:00 to 17:30 with breaks. The agenda follows the exam domains and the final day includes a mock exam.
What is the exam format?
AWS Certified Machine Learning – Specialty (MLS-C02): 65 questions (multiple-choice and multiple-response), 170 minutes, closed book, Test centre or online proctored via Pearson VUE or PSI. Pass mark: Scaled score of 750 (100–1000 scale). Confirm the current version with the awarding body when you book.
Is the exam included?
Yes. Outside India the fee includes one certification exam attempt. Retakes are booked and paid directly with the awarding body.
Are there prerequisites?
There are no formal prerequisites from AWS. Recommended: solid Python, basic statistics, and 1–2 years working with ML or data workflows; familiarity with AWS helps. Bring a laptop with admin rights, modern browser, Python 3.10+ (Anaconda/Miniconda), and a GitHub account.
What certificate will I receive?
Two credentials. MindClick issues a certificate of completion for 80 contact hours to every attendee. Amazon Web Services (AWS) issues the AWS Certified Machine Learning – Specialty (MLS-C02) certification when you pass the exam and meet its requirements. 3 years from date earned.
Is MindClick an accredited training partner for this certification?
MindClick provides training and exam preparation and is not an accredited or authorised partner of Amazon Web Services (AWS). The exam is administered by AWS through Pearson VUE and PSI.
KEEP EXPLORING
More ways to move forward.
Related training from the course catalog.
Machine Learning A-Z
Six-day (44-hour) course where you build and evaluate machine learning models in Python and R, practise labs daily, and prepare for certification.
Python for Data Analysis
Three-day Python for Data Analysis course where you clean, transform, visualise, and explore datasets using pandas, NumPy, and matplotlib with practical labs.
Deep Learning Specialization
Eight-day, 60-hour deep learning course where you build and train neural networks, CNNs, RNNs and transformers in TensorFlow and PyTorch.
Microsoft Power BI Data Analysis
Build practical skills in data preparation with power query and data models and dax calculations.