For my program in stats, I read the elements of Statistical learning, still my favorite book. I read Applied Predictive Modeling by Max Khun. I would recommend this book to anyone, it's a good read.
@@seetsamolapo5600 I have all three. I used elements of statistical learning in grad school I still open it up sometimes, it's a good reference. Introduction to statistical Learning is the baby brother to this book, also a good book. It focus is R, so if you're learning Python first I'd probably get a different book so you can also follow along with the code, as well as, the mathematical/statistics principles. If you are using R, Another good book would be Tidy Modeling With R, also written by Max Khun, it's an updated version of his predictive modeling book. You can find these free online and see which one you like before getting a physical copy.
Well I would comment on that book as a general view of machine learning The most important part is in chapter 1 and chapter 2 and the rest of it I recommend everyone should go through the details yourself for example RPCA U should able to build up your own script from scratch and keep doing new project to keep your mind strong
I'll work on it, they take a bit more time given all the reading. I'm not sure if you know but I do have a book review playlist: ruclips.net/p/PLBfqPS8Xvt2AcW5gWsxiATx0IGdZcPXZD
Im currently going through this book, currently on chp. 3 ... one thing for sure if u really want to enjoy or better understand this book, learn complete python before purchasing this book ...
advise me PLZ i read grokking machine learning book , do i need to read hands on Machine Learning with Scikit-Learn and TensorFlow also or not? Hands on Machine Learning with Scikit-Learn and TensorFlow will help me more and get me lots of additional knowledge or not
It depends what areas you are looking to learn. The table of contents in this book looks to cover more than Grokking. However I would consider, An Introduction to Statistical Learning for more theory. It is free online.
From an academic perspective Bayesian inference is another tool a quant can use to help solve problems. A team I was on considered applying it to a special project however the project got scrapped due to time constraints. I'm sure there are areas where it is the best option however for my work, we haven't really use it. Like all methods there are a lot of assumptions and getting these correct can be a challenge.
Solutions to these exercises are available in appendix A. Where can i find this Appendix A for hands on machine learning with scikit-learn and tensorflow 2
I will consider adding it to the book review list. I'm looking around for a few new books to review. Some of my data science friends have mentioned this is a good book.
You really need to know quite a bit of math and statistics to build reliable models. Since I come from an economic background, I find this book helpful (my affiliate link). It covers some of the basics such as using gradients to find min and max points (used in neural networks for example). Mathematics for Economists amzn.to/2SJ1l3K
@@DimitriBianco Hey, thanks for this. Actually, I am from an Arts background. I am currently working in the Data Analyst field. But I am interested in learning ML.
There is not a specific chapter on features engineering but it does discuss briefly what feature engineering is. Realistically though, feature engineering will come with expertise in what you are modeling. The features used in finance would be very different than features used in say marketing analytics.
Hi Dimitri great content as always! Would love more book reviews in the future. I'm currently a freshman entering university and would love some honest advice. I am studying Accountancy and Finance and am interested (i think) in entering the more traditional finance roles e.g. FP&A, corp fin&strategy etc. However, I would like to keep my options. I was thinking of taking a minor in Mathematics so that I meet the pre-reqs for post-grad in a more quantitative field such as a MSc in stats or comp finance, or to simply have the skills needed to self-study in the future. I would be able to take ~8 courses, incl. Calculus 1-3, Linear Algebra 1-2, probability, statistics and possibly real analysis and ODE. Do you think this is a good idea? If so, are there any other courses you think I should take instead (e.g. regression, stochastics etc.)? Or do you think it would be a better idea for me to take a minor in Computing, where I would get a strong foundation in programming, data structures, algorithms etc. ? The minor would probably be immediately more useful and relevant. Thanks once again, really enjoy your content!
As someone who did a Bachelor of Accounting, don't bother unless you're planning on becoming a CPA. It's a complete waste of time and these days is the equivalent of doing a Bachelor of Arts. If I were you, I'd focus my degree entirely on Computer Science, Mathematics and some Economics/Finance as well. So if you can double major in Comp Sci and Finance and then minor in Maths, that would work.
For going the quant route you really have to be all in. A math or statistics minor could help but in most cases it won't be enough to get into a good quant masters program. If you want other options besides finance and accounting, I would go with the computer science (CS) minor. The reason being, tech firms aren't sticklers about the degree but care more about the skills. You can also apply your CS knowledge to a variety of jobs.
@@DimitriBianco Thanks for the advice, really appreciate it. I was leaning towards the math minor, as it seemed to fulfill the minimum pre-requisites of many quantitative MSc (e.g. stats, econs, comp fin, FE etc.) at top unis in US/UK/locally (am from Asia), hence giving me the avenue to move into a more quantitative field if I wanted in the future. I will have to give it more thought, am still really perplexed about my choice of majors/minors...
I typically spend a lot of time searching for good books before I start reading. It can be expensive both in money and time to waste on bad books. However I have done a dual book review where I discuss my dislike of the two books. I don't believe I give them star reviews however I don't recommend people buy them. ruclips.net/video/jYpRAJHFBCE/видео.html
Does the book by Christopher Bishop provide any additional value for someone who has already gone through the Deep learning book( by Goodfellow and friends) and intro to statistical learning?
I'm not the biggest fan of Bishop's book (Pattern Recognition and Machine learning) however it will cover different material than Deep Learning. The deep learning book won't cover topics such as Markov models, linear regression, or Bayesian. I haven't covered "Intro to Statistical Learning" however it should cover similar topics as Bishop's book.
Reading this book now. It's pretty friendly for beginners.
I'd agree with that. It was a fun book to work through.
Where can i get this book in cheap price ?
For my program in stats, I read the elements of Statistical learning, still my favorite book. I read Applied Predictive Modeling by Max Khun. I would recommend this book to anyone, it's a good read.
Between this book and Introduction to Statistical Learning?
@@seetsamolapo5600 I have all three. I used elements of statistical learning in grad school I still open it up sometimes, it's a good reference. Introduction to statistical Learning is the baby brother to this book, also a good book. It focus is R, so if you're learning Python first I'd probably get a different book so you can also follow along with the code, as well as, the mathematical/statistics principles. If you are using R, Another good book would be Tidy Modeling With R, also written by Max Khun, it's an updated version of his predictive modeling book. You can find these free online and see which one you like before getting a physical copy.
great book on machine learning....
Really liked this video, now I know what to expect from the book.
Well I would comment on that book as a general view of machine learning The most important part is in chapter 1 and chapter 2
and the rest of it I recommend everyone should go through the details yourself for example RPCA U should able to build up your own script from scratch
and keep doing new project to keep your mind strong
Please review books more frequently. Great review
I'll work on it, they take a bit more time given all the reading.
I'm not sure if you know but I do have a book review playlist:
ruclips.net/p/PLBfqPS8Xvt2AcW5gWsxiATx0IGdZcPXZD
Incredible content! Coming here to congratulate you from Brazil, your channel is really helping me
Happy to hear that!
Im currently going through this book, currently on chp. 3 ...
one thing for sure if u really want to enjoy or better understand this book, learn complete python before purchasing this book ...
Love the videos ❤️....looking forward for more book reviews ❤️❤️❤️
Which books do you recommend as companions (for Math, and other lacking areas) of this Hands-on ML book?
I haven't read it but "The Elements of Statistical Learning" comes highly recommended by many people I respect. It is on my reading list.
thanks for comprehensive explanation
Good timing mam actually looking to buy this but didn't sure. It's quite expensive. Thanks
I don't know a thing about ML. I am a Python programmer, have done a some matrix stuff before, is this a good book for a complete beginner for me?
Yes this will give you a good introduction.
What are good maths book for ML and DL ?
calculus by james, itsl , intro to probability. i am following.
advise me PLZ
i read grokking machine learning book , do i need to read hands on Machine Learning with Scikit-Learn and TensorFlow also or not?
Hands on Machine Learning with Scikit-Learn and TensorFlow will help me more and get me lots of additional knowledge or not
It depends what areas you are looking to learn. The table of contents in this book looks to cover more than Grokking. However I would consider, An Introduction to Statistical Learning for more theory. It is free online.
Hi Dimitri,
What is your take on Bayesian inference? Is it used a lot/at all in your work/as a statistican/as a quant?
From an academic perspective Bayesian inference is another tool a quant can use to help solve problems. A team I was on considered applying it to a special project however the project got scrapped due to time constraints. I'm sure there are areas where it is the best option however for my work, we haven't really use it. Like all methods there are a lot of assumptions and getting these correct can be a challenge.
Hi can you make a video about the deep learning with python book ? And is it suitable for a beginner in neural networks?
If you are referring to the one by Chollet, I think it is a great book for beginners and well thought out.
Bianco, what about: Machine Learning for Asset Managers By Lopes de Prado?
I haven't read that one but Lopez de Prado's books are a lot better quality than most ML books for finance. I've debated on buying that book.
Awesome video! it would be pretty cool if you did a video on your goals, it would be great to see what a quants goals are today in the industry!
I will consider it.
Hey Dimitri! Could you consider making a future video on fintech start-ups?
Thanks brother. Good info for me
Solutions to these exercises are available in appendix A.
Where can i find this Appendix A for hands on machine learning with scikit-learn and tensorflow 2
Page 719 at the back of the book.
Hey Dimitri, great video! Do you ever plan on doing a book review for Elements of Statistical Learning?
I will consider adding it to the book review list. I'm looking around for a few new books to review. Some of my data science friends have mentioned this is a good book.
seems to be a great book! I'll add on my wishlist
I have both of hands on machine learning with python and pyhton for deep learning how can I use them
Do I need to learn Python before following this book? I know only the basics of Python.
Knowing the basics should be enough. The code is very simple and straight forward.
@@DimitriBianco Thank you for your reply. I'll buy the book and start learning ML later this month. :)
@@DimitriBianco And what about Maths?
You really need to know quite a bit of math and statistics to build reliable models. Since I come from an economic background, I find this book helpful (my affiliate link). It covers some of the basics such as using gradients to find min and max points (used in neural networks for example).
Mathematics for Economists
amzn.to/2SJ1l3K
@@DimitriBianco Hey, thanks for this. Actually, I am from an Arts background. I am currently working in the Data Analyst field. But I am interested in learning ML.
does this contains feature engineering ,feature selection things like contents??
There is not a specific chapter on features engineering but it does discuss briefly what feature engineering is. Realistically though, feature engineering will come with expertise in what you are modeling. The features used in finance would be very different than features used in say marketing analytics.
I would like to start in ML's field. This book looks great but what other book should I use to supplement the theory part?
Pattern Recognition and Machine Learning by Christopher M. Bishop
Thanks man, love your content :)
@@ignacioschulz8182 thanks for being a part of the channel!
Hi Dimitri great content as always!
Would love more book reviews in the future.
I'm currently a freshman entering university and would love some honest advice. I am studying Accountancy and Finance and am interested (i think) in entering the more traditional finance roles e.g. FP&A, corp fin&strategy etc.
However, I would like to keep my options. I was thinking of taking a minor in Mathematics so that I meet the pre-reqs for post-grad in a more quantitative field such as a MSc in stats or comp finance, or to simply have the skills needed to self-study in the future. I would be able to take ~8 courses, incl. Calculus 1-3, Linear Algebra 1-2, probability, statistics and possibly real analysis and ODE.
Do you think this is a good idea? If so, are there any other courses you think I should take instead (e.g. regression, stochastics etc.)?
Or do you think it would be a better idea for me to take a minor in Computing, where I would get a strong foundation in programming, data structures, algorithms etc. ? The minor would probably be immediately more useful and relevant.
Thanks once again, really enjoy your content!
As someone who did a Bachelor of Accounting, don't bother unless you're planning on becoming a CPA. It's a complete waste of time and these days is the equivalent of doing a Bachelor of Arts. If I were you, I'd focus my degree entirely on Computer Science, Mathematics and some Economics/Finance as well. So if you can double major in Comp Sci and Finance and then minor in Maths, that would work.
For going the quant route you really have to be all in. A math or statistics minor could help but in most cases it won't be enough to get into a good quant masters program. If you want other options besides finance and accounting, I would go with the computer science (CS) minor. The reason being, tech firms aren't sticklers about the degree but care more about the skills. You can also apply your CS knowledge to a variety of jobs.
@@DimitriBianco Thanks for the advice, really appreciate it.
I was leaning towards the math minor, as it seemed to fulfill the minimum pre-requisites of many quantitative MSc (e.g. stats, econs, comp fin, FE etc.) at top unis in US/UK/locally (am from Asia), hence giving me the avenue to move into a more quantitative field if I wanted in the future.
I will have to give it more thought, am still really perplexed about my choice of majors/minors...
Why buy this book if there is good online documentation, udemy courses, RUclips, medium, Twitter?
is still this book recommended for 2022 ?
I would still recommend it. There might be some code that is outdated however it teaches the basics really well.
@@DimitriBianco Thanks a lot ;
will be any update of this book ? or no news ?
thanks in advance .
@@DimitriBianco How about ISLR which is better for beginner this one or ISLR?
Whats happening with your merch?
It's still being sold through TeeSpring. There should be a list of items available under each video now.
do you still recommend this book for 2024??
Yes. The video coming out this Sunday will discuss it again as part of a list of books.
i'm sort of curious which texts you'd rate like 1/5 or less, lol
Those books he doesn't review
I typically spend a lot of time searching for good books before I start reading. It can be expensive both in money and time to waste on bad books. However I have done a dual book review where I discuss my dislike of the two books. I don't believe I give them star reviews however I don't recommend people buy them.
ruclips.net/video/jYpRAJHFBCE/видео.html
Hi! I'm from Indonesia. I like your videos, but it will be so much better if you have timestamps in the description, thank you very much :D
Ada rekomendasi buku buat belajar data science ga bro
Does the book by Christopher Bishop provide any additional value for someone who has already gone through the Deep learning book( by Goodfellow and friends) and intro to statistical learning?
I'm not the biggest fan of Bishop's book (Pattern Recognition and Machine learning) however it will cover different material than Deep Learning. The deep learning book won't cover topics such as Markov models, linear regression, or Bayesian. I haven't covered "Intro to Statistical Learning" however it should cover similar topics as Bishop's book.
What is up with so many Asians and LatAms being interested in “quant” finance?
👍👍👍