So, about 18 months ago I created a video on Safari about how A.I. could benefit Data Science (DS and AI). Even though at that time I was still figuring things out regarding how educational videos work, the vid was immensely popular and even today still attracts lots of views. Considering that all of my recent videos are (much) better than that one, at least technically, this is quite intriguing.
Anyway, fast forward to September last year. As I was walking in the streets of suburban Seattle, thinking about what to do next (my Data Science Mindset, Methodologies, and Misconceptions book had just been released), I decided to write another book, one about A.I. since this topic continued to fascinate me, while it was becoming a popular topic among various data scientists. So, I pitched the idea of a new book to Steve Hoberman and after sorting out the details, we got a contract going. However, due to various reasons we decided to start the book in January.
The whole project was quite a turbulent one, with my co-author dropping out around March, leaving me in a very difficult situation. Yet, I decided that the book was worth completing. Fortunately, another data scientist / A.I. expert decided to join me in this endeavor, Yunus E. Bulut, who I got acquainted with through Thinkful. Long story short, after a few discussions about the project he had a contract of his own as a co-author.
Three months later, the first draft was complete. Of course the book went through a lot of revisions since then, partly because the technology was changing and partly because there were a lot of topics in this book, which was difficult to coordinate and merge into a coherent whole. Also, at one point Julia reached adulthood as a programming language (v. 1.0) so we had to update the code for the chapters that had programs in Julia.
So, after a feverish summer, plagued by heat waves and other obstacles, we finished the edits (at least the most important ones, since a book is never really finished!) and the book went to the press. Now, it is finally available for you to buy at whatever vendor you prefer. Check out the publisher's site for more details. Cheers!
With all the plethora of material out there for data science education, it is easy to get overwhelmed and even confused about what to study and how much time, money, and effort to put into it. Enter evaluation of data science material, a concise strategy for tackling this issue. In this 24 minute video, I talk about the various aspects of data science material, criteria for evaluating it, the matter of resources required to delve into this material, and some useful things to have in mind in your data science education efforts. Whether you are a newcomer to the field or a more seasoned data scientist, you have something to learn about data science (I know I do!) and this video can hopefully aid you in that. You can find it on Safari.
Note that in order to be able to view this video in its entirety, you'll need a subscription for the Safari platform. Also, it's important to remember that this video can offer you a framework for evaluating the data science material; you'll still need to find that material though and put the effort to study it, in order to make the most of it. The video can only help you organize your efforts more efficiently. Enjoy!
Last week I’ve finished my part of the final corrections stage of the new technical book I’d been working on for the past few months. My co-author, Yunus, has done the same, so the book should be in the press later this month! Hopefully, you should be able to purchase it soon, either from the publisher’s site, or from some other vendor (e.g. Amazon). Just wanted to share that with you all. Once the book is out there, I’ll be sure to make an announcement about it here on this blog. Cheers!
A/B testing is a crucial methodology / application in the data science field. Although it mainly relies on Statistics, it has a remained quite relevant in this machine learning and AI oriented era of our field. It's no coincidence that in Thinkful that's one of the first things data science students learn, once they get comfortable with descriptive Stats and basic data manipulation. So, I decided to do a video on this topic to help those interested in learning about it get a good perspective of it and understand better its relationship with Hypothesis Testing. It is my hope that this video can be a good supplement to one's learning on the subject. Enjoy!
I was never particularly fond of this unsupervised learning methodology that’s under the umbrella of machine learning. It’s not that I didn’t see value in it, but the methods that were available for it when I started delving into it were rudimentary at best and fairly crude. In fact, if I were to do a PhD now, I’d choose a clustering-related topic since there is so much room for improvement that even a simple idea for improving the most popular clustering methods out there is bound to improve them!
However, the fact that data science researchers and machine learning engineers in particular haven’t spent much time looking into clustering doesn’t make clustering a bad methodology. In fact, I’d argue that it’s one of the most insightful ones and it plays an important role in many data science projects, particularly in the data exploration stage.
The key issues with clustering are:
1. The whole set of distance metrics used
2. The fact that the vast majority of clustering methods yield a (slightly) different result every time they are run
3. The need of an external parameter (K) in most clustering methods used in practice, in order to define how many clusters there are
4. The fact that it’s very shallow in its results
There may be more issues with clustering, but these are the most important ones I’ve found. So, if we were to rethink clustering and do it better, we’d need to address each one of these issues. Namely:
1. A new set of distance metrics would be needed, metrics that are not influenced by the dimensional “noise” so much, in the case of many dimensions in the dataset.
2. The option for a deterministic clustering method, one that would optimize the centroid seed before starting the whole clustering process
3. An optimization process would be in place so as to find the best number of clusters. This should include the possibility of a single cluster, in the case where there isn’t enough diversity in the dataset.
4. A multi-level clustering option needs to be available, much like hierarchical clustering but in reverse, i.e. start with the main clusters in the dataset and gradually dig deeper into levels of sub-clusters.
Now, all this may sound simple but it’s not as easy to put into practice. Apart from an in-depth understanding of data science, a quite refined programming ability is needed too, so that the implementation of this clustering approach can be efficient and scalable. Perhaps all this is not even possible with the conventional data analytics framework, but there is not a single doubt in my mind that it is possible in general, and if a high-performance language is used (e.g. Julia), it is even practically feasible.
Naturally, a clustering framework like this one would require a certain level of A.I. to be used. This doesn’t have to be an ANN though, since A.I. can take many forms, not just network-based ones. Whatever the case, conventional statistics-based methods may be largely inadequate, while the very basic machine learning methods for clustering may not be sufficient either.
This illustrates something that many data science practitioners have forgotten: that data science methods evolve, just like other aspects of the craft. New tools may be intriguing, but equally intriguing are the conventional methodological tools, especially if we were to rethink them from a more advanced perspective. This can be beneficial in many ways, such as opening new avenues of data analytics and even synthesizing new data. This, however, is a story for another time...
So, my publisher has been co-organizing this conference for a few years now, and this September it is going to be in Düsseldorf, Germany. What's so special about it? Well, I'll be participating in it too, as a speaker. But regardless of that, the DMZ conference has grown a lot since it first started and now covers a variety of topics, not just related to Data Modeling. Also, just like other good conferences, DMZ has a variety of good technical books made available, plus if you register for the conference using the code DMZEU2018_VOULGARIS you can get a 25 Euro discount on any book-related purchase you make (that's about $29 worth of reading material). So, check it out, when you get the chance, at https://datamodelingzone.com.
It’s not the programming language, as some people may think. After all, if you know what you are doing, even a suboptimal language could be used without too much of an efficiency compromise. No, the biggest mistake people make, in my experience, is that they rely too much on libraries they find as well as the methods out there. This is not the worst part though. If someone relies excessively on predefined processes and methods, the chances of that person’s role getting automated by an A.I. are quite high. So, what can you do?
For starters, one needs to understand that both data science and artificial intelligence, like other modern fields, are in a state of flux. This means that what was considered gospel a few years back may be irrelevant in the near future, even if it is somewhat useful right now. Take Expert Systems, for example. These were all the rage during the time when A.I. came out as an independent field. However, nowadays, they are hardly used and in the near future, they may appear more anachronistic than ever before. That’s not to say that modern aspects of data science and A.I. are going to wane necessarily, but if one focuses too much on them, at the expense of the objective they are designed for, that person risks becoming obsolete as they become less relevant.
Of course, certain things may remain relevant no matter what. Regardless of how data science and A.I. evolve, the k-fold cross-validation method will be useful still. Same goes with certain evaluation metrics. So, how do you discern what is bound to remain relevant from what isn’t? Well, you can’t unless you try to innovate. If certain methods appear too simple, for example, they may not stick around for much longer, even if they linger in the textbooks. Do these methods have variants already that outperform the original algorithms? Are people developing similar methods to overcome drawbacks that they exhibit? What would you do if you were to improve these methods? Questions like this may be hard to answer because you won’t find the necessary info on Wikipedia or on StackOverflow, but they are worth thinking about for sure, even if an exact answer may elude you.
For example, I always thought that clustering had to be stochastic because everyone was telling me that it is an NP-hard problem that cannot be solved efficiently with a deterministic method. Well, with this mindset no innovations would ever take place in that method of unsupervised learning, would it? So, I questioned this matter and found out that not only are there ways to solve clustering in a deterministic way, but some of these methods are more stable than the stochastic ones. Are they easy? No. But they work. So, just like we tend to opt for mechanized transportation today, instead of the (much simpler) horse and carriage alternative, perhaps the more sophisticated clustering methods will prevail. But even if they don’t (after all, there are no limits to some people’s detest towards something new, especially if it’s difficult for them to understand), the fact that I’ve learned about them enables me to be more flexible if this change takes place. At the same time, I can be more prepared for other changes in the field, of a similar nature.
I am not against stochastic methods, by the way, but if an efficient deterministic solution exists for a problem, I see no reason why we should stick with a stochastic approach to that problem. However, for optimization related scenarios, especially those involving very complex problems, the stochastic approach may be the only viable option. Bottom line, we need to be flexible about these matters.
To sum up, learning about the conventional way of solving data-related problems, be it through data science methods, or via A.I. ones, is but the first step. Stopping there though would be a grave mistake, since you’d be depriving yourself the opportunity to delve deeper into the field and explore not only what’s feasible but also what’s possible. Isn’t that what science is about?
When I started my life-long journey in the world of data analytics (which morphed into Data Science and modern AI-based predictive analytics systems), it was through academia. I even did a post-doc at one point, which although paid the bills, it was the worst-paying job I’ve ever had during my career. Yet, as long as there were things to learn and challenges to overcome, I was willing to see past that.
As I matured, I realized that the only thing that mattered in that strange world, if you were to have a career in it, was publications. As I enjoyed writing, I gave it a shot. However, the needlessly long waiting time for any feedback, the low quality of that feedback, and the overall time it took for something to get published, put me off eventually. After that, I decided to pursue a career, any career, in the real-world, as at least here there is more meritocracy and smaller waiting times, enabling a much faster growth.
A few months ago, I was approached by a big-time academic publishing house for an article in their encyclopedia of big data. I was surprised to see that after so many years they had come to be more progressive about the whole publications related business. As the topic was down my alley, I decided to accept their offer. At the time I felt that this would be my way of giving back to the data science programming community. I only asked that the companies I work with get mentioned in the article so that they can at least justify my being distracted by this project. The academic publisher accepted and said that these companies would be mentioned as my affiliations. I even provided their location details afterwards, so that they were going to be represented fully.
Months later, I got some feedback, some really minor corrections, that I took care of promptly. Finally, last month the article was published. I was pleased, for a couple of minutes, till I realized that the affiliations were all screwed up. Up to this day I am not sure how this could happen. It would take a whole new level of incompetence to mess up such a simple task, more than I was used to seeing through my academic life. Of course, mistakes happen and since I’m not perfect either, I politely asked for corrections on this part of the article. I had to do this twice, since apparently the first time they must have forgotten about it (apparently these corrections were not a priority to them). Up to this day, the article remains uncorrected, since clearly this 2-minute task is just too much for them to handle, or perhaps there isn’t much of a motivation.
If there was a slight chance of me ever working in an academic setting again, e.g. by writing articles like that one or academic papers, this is gone as this event proved what a colossal waste of time it is working with this sort of bureaucracy. Perhaps for you it’s different because you have higher tolerance or lower self-esteem (or maybe both) and you can put up with these clowns. However, if you are on a crossroad in your career in our field, be sure to explore your options wisely before being tempted to compromising with an academic publication gig. More often than not, it would not be worth your time, while all the other alternatives would be more rewarding.
UPDATE: finally they managed to update the affiliations bit. I wonder if this article had anything to do with it! It's doubtful that I'll change my view on the academic publications matter any time soon though.
Bias-Variance Trade-Off for Data Science & Backing Up and Wiping Out Sensitive Data Videos Are Now Online
This past week I've had some time off work as my CEO was on vacation. As a result I did 2 videos, not just 1. Here they are:
The Bias-Variance Trade-Off: when you have a model that favors a certain class or a certain set of values, you have high bias, while you have a model whose predictions are all over the place, you have high variance. Could you find a compromise between the two? And how does all this relate to the model's fitness? This video includes a few examples too, for classification and regression problems, to cement the concepts introduced.
Backing Up and Wiping Out Sensitive Data: you probably have heard of this topic and perhaps even apply it to some extent, since taking care of sensitive data is a good cyber-security habit to have, plus it's not new either. However, there is much more to it than that, like which storage media are best for back-up, how you can handle sensitive data on your computer without leaving a trace, and what software is out there that helps make that happen.
Why Articles on Social Media about Programming for Data Science Seem to Be Straight Out of a Time Capsule
Data science related topics sell, no doubt about that. This is great is you are interested in the field and want to learn more about it, especially practical things that can offer you some orientation in the field. Since programming is a key component of data science, it makes sense to pay attention to material along these lines, particularly if you are new to this whole matter.
How the Situation Is Today
Fortunately there is an abundance of articles on this topic, especially on the social media. However, not everyone who writes such articles is up-to-date on this subject since many of these “expert” tech writers are not forward thinking data scientists themselves. Best case scenario, they have spend a few minutes on the web, probably focusing on the results on the first page of a search engine for the bulk of their material. And shocking as it may be, this material may be geared more towards what’s more popular rather on what’s more accurate. Alternatively, they may have relied on what some data science guru once said on the topic, information that may no longer be particularly relevant. Apart from that, the writers who delve into the production of this sort of articles (or infographics in some cases) have their own biases. Probably they took a programming course at university so if a particular programming platform comes up on their “research” they may be more likely to highlight it. After all, this would make them knowledgeable since they have hands-on experience on that platform, even if it’s not that useful to data science any more. What’s more, many people who write about these topics don’t want to take risks with newer things. It’s much safer to mention languages that everyone knows about and which have a large community around them, than mention newer ones that may be despised by the hardcore users of older coding platforms.
Hope for the Future
For better or for worse, an article on the social media has a limited life span. After all, its purpose is mainly to get enough people to click on a particular link where a given site serves ads, so that the people owning the site can get some revenue from said ads. Therefore, if the article is forgotten in a week, its producers won’t lose any sleep over it. Books and subscription-based videos are not like that though. Neither are technical conferences. So, since the new trends are geared more towards this kind of platforms to become well-known, they are not that much hindered by social media misinformation. After all, if a programming language is good, this is something that will eventually show, even if the fan-boys of the more traditional languages would sooner die than change their views on their favorite coding platforms.
What You Can Do
So, instead of getting swayed by this or the other “expert” with X thousand followers (many of whom are probably either bots or bought followers), you can do your own research. Check out what books are out there on the various programming languages and if they hint towards applicability in data science. Check out videos on Safari and other serious educational platforms. Look at what new language conferences are out there and how they cover data science related topics. And most importantly, try some of these languages yourself. This way you’ll have some more reliable data when making a decision on what language is most relevant and most future-proof in our field, rather than blindly believe whatever this or the other “expert” on the social media says.
Zacharias Voulgaris, PhD
Passionate data scientist with a foxy approach to technology, particularly related to A.I.