Chevron Left
Retour à How to Win a Data Science Competition: Learn from Top Kagglers

Avis et commentaires pour d'étudiants pour How to Win a Data Science Competition: Learn from Top Kagglers par Université HSE

1,113 évaluations
274 avis

À propos du cours

If you want to break into competitive data science, then this course is for you! Participating in predictive modelling competitions can help you gain practical experience, improve and harness your data modelling skills in various domains such as credit, insurance, marketing, natural language processing, sales’ forecasting and computer vision to name a few. At the same time you get to do it in a competitive context against thousands of participants where each one tries to build the most predictive algorithm. Pushing each other to the limit can result in better performance and smaller prediction errors. Being able to achieve high ranks consistently can help you accelerate your career in data science. In this course, you will learn to analyse and solve competitively such predictive modelling tasks. When you finish this class, you will: - Understand how to solve predictive modelling competitions efficiently and learn which of the skills obtained can be applicable to real-world tasks. - Learn how to preprocess the data and generate new features from various sources such as text and images. - Be taught advanced feature engineering techniques like generating mean-encodings, using aggregated statistical measures or finding nearest neighbors as a means to improve your predictions. - Be able to form reliable cross validation methodologies that help you benchmark your solutions and avoid overfitting or underfitting when tested with unobserved (test) data. - Gain experience of analysing and interpreting the data. You will become aware of inconsistencies, high noise levels, errors and other data-related issues such as leakages and you will learn how to overcome them. - Acquire knowledge of different algorithms and learn how to efficiently tune their hyperparameters and achieve top performance. - Master the art of combining different machine learning models and learn how to ensemble. - Get exposed to past (winning) solutions and codes and learn how to read them. Disclaimer : This is not a machine learning online course in the general sense. This course will teach you how to get high-rank solutions against thousands of competitors with focus on practical usage of machine learning methods rather than the theoretical underpinnings behind them. Prerequisites: - Python: work with DataFrames in pandas, plot figures in matplotlib, import and train models from scikit-learn, XGBoost, LightGBM. - Machine Learning: basic understanding of linear models, K-NN, random forest, gradient boosting and neural networks. Do you have technical problems? Write to us:

Meilleurs avis

28 mars 2018

Top Kagglers gently introduce one to Data Science Competitions. One will have a great chance to learn various tips and tricks and apply them in practice throughout the course. Highly recommended!

9 nov. 2017

This course is fantastic. It's chock full of practical information that is presented clearly and concisely. I would like to thank the team for sharing their knowledge so generously.

Filtrer par :

26 - 50 sur 273 Avis pour How to Win a Data Science Competition: Learn from Top Kagglers

par Aymen S

26 févr. 2020

This course is the biggest achievement in my Coursera until now, I wanna thank every one of the organizers of the course. For me it is the most advanced course related to data science that one can take because it's a combination between theory and practice, and I have learned a lot of staffs like how to deal with overfitting, mean encoding, lag features and stacking .


17 juil. 2020

muy buen curso en el que se enseñan técnicas avanzadas de Machine Learning.

es un poco complejo para personas que no tengan unas buenas bases de conocimiento en el tema de Machine learning.

(very good course in which advanced Machine Learning techniques are taught.

It is a bit complex for people who do not have a good knowledge base on the subject of Machine learning.)

par Alouini M Y

18 oct. 2019

A very challenging ML course but worth all the efforts. This course contains various interesting analyses of techniques to get better at ML modelling: from mean encoding (and how to do properly) to nearest neighbors features and model stacking. This is very useful for Kaggle challenges specifically but is valuable for day-to-day data science tasks more generally.

par Margarita C

7 nov. 2019

This course is awesome. The more effort I invested in it - the more results I got, and I feel like I haven't reached the limit. The course is very thought-out, the tests and programming assignments are great, teachers are inspiring. I enjoyed every part of it!

par Stephane H

10 avr. 2019

Great course, truly invaluable information in there, also the hardest i've ever done, took me months and a couple hundred hours. The knowledge and experience you gain is incredible, not for the faint of heart though.


15 juil. 2020

Thank you for sharing your knowledge. It is a very complete course, it has a very insightful material. I strongly recommend this course to people with a good background to take advantage of all the content.

par Алексей Ш

29 mai 2020

Спасибо авторам курса! На мой взгляд им удалось пройти по тонкой грани между достаточностью и избыточностью информации. Все информация и дополнительные ссылки - очень полезны. Отличный курс!

par Aryan G

30 mai 2020

Certainly one of the best and informative courses on competitive data science. If you are interested in this field, no better way than to start from here.

par Yulia R

25 mars 2021

awesome course, videos about leaks and competition pipelines are especially interesting

par Siddhant D

4 juin 2020

Best course on machine learning I have ever had. Learned a lot every day.

par Xiukun H

25 févr. 2019

Great course to learn practical skills. I love the painful final project.

par Jin K

14 juin 2020

Excellent course for Kaggler. All participants should take this course!

par Bazaliy V

17 août 2020

Great place to learn very useful practical skills for Data Scientist.


15 déc. 2020

Excelente, muy exigente el nivel, pero muy completo el curso

par Dhruv N

22 août 2020

Best course i ever had

par yanqiang

29 oct. 2018


par Alex M

18 juin 2021

T​his course helped me not only in Kaggle competitions but also it's a fantastic tutorial for advanced Machine Learning methods! I really recommend to pass the course with Alice Zheng & Amanda Casari book. I mean "Feature Engineering for Machine Learning".

T​hings in course that weren't appropriate for me:

1​) In advanced feature II (4th week) there are interesting approaches, but no code examples for them :(

2​) knn-assignment from the 4th week was one big nightmare: I had to change files directory in the assignment by myself. This problem was encountered by many other course participants.

B​ut in general, "How to Win a Data Science Competition: Learn from Top Kagglers" is amazing course which gave me self-confidence in many advanced methods! Thank you.

par Juan C A G

29 nov. 2020

I consider this a very advanced and time consuming course. I enjoy learning from the experience of the instructors, considering they know a lot about the competition. However, I found difficult to follow many topics because a lot of previous knowledge is required. Besides this, the spoken English is not always good and the subtitles are mistaken many many times. All in all I found the course good in what they taught. Improvements are required in the methodology and English language.

par Голубев К О

27 sept. 2018

Great course with excellent tutors. 1C Predict Price Competiton - the best InClass Kaggle competition in which I took part.

But, IMHO, there's not enough practice. For example: it's very useful to exercise on different validation strategies or on stacking of something more, than 2 simple models. Also there's a mistakes in KNN notebook and unclear instrustions.

par Aman S

3 juin 2019

Teaching style is not engaging at all. I am very confused

par Milos V

8 mars 2019

Very interesting course, and the most practical and useful one. However, lecture are usually too theoretical and super-simple, while assignments are tough and very code oriented. So often there is no real connection between the two (except for Dmitry Altukhov). And final project is too difficult in sense that my Alienware 16 RAM was not enough, so I had to go to Google Cloud Platform. Also, I am not sure is anybody who is learning Machine Learning possible to do the final task in "6 hours" as solely runs could last for a day...

par Murat E

22 déc. 2020

Instructors are very valuable teachers and I learned a lot. However:

1) course content is getting old. Some of the points mentioned have changed. Content should be updated. Requiring eariler versions of python libraries is diminishing returns since I had to troubleshoot what went wrong instead of focusing on learning material.

2) Coursera platform gave me lots of headaches. Containers are not suitable for running the final project and I had to optimize memory usage and ran really slow.

par Sailesh G

7 avr. 2020

It was just not working for me. Perhaps the fault is mine, because I found it hard to grasp and was always trying to get on the same page. The course presentation only added to the challenge. One thing for sure, beginner (or intermediates) should stay away from this one until you're ready. I may perhaps revisit this course if I feel right, but that's a long way off.

Thank you.

par Lun Y

7 mai 2019

There are too many things need the learner to investigate by themselves. We are here to learn but not guess. And the condition to close the course is very hard to achieve. I'd say it is not a well designed course including contents and how they are organized.

par Mithun G

14 janv. 2018

Content is really good. But delivery is at times incomprehensible. Assignments questions are also not very clear