Started this discussion. Last reply by Vincent Granville on Tuesday. 4 Replies 0 Likes
If you don't like using black-box R functions, or you don't have access to these functions, here are simple options to simulate deviates from various distributions. They can even be implemented in…Continue
Started this discussion. Last reply by Vincent Granville May 24. 1 Reply 0 Likes
Started this discussion. Last reply by Daren Scot Wilson May 27. 6 Replies 1 Like
We all know that exponential functions grow faster than polynomials. Let us consider the following function: f(n) = n^a ⋅ (log n)^b ⋅ (log log n)^c ⋅ (log log log n)^d⋯ where the leading coefficient…Continue
Started this discussion. Last reply by Vincent Granville May 4. 1 Reply 0 Likes
Let us consider the sequence x(n+1) = { b + x(n) } with x(0) = 0. Here the brackets represent the fractional part function. Thus x(n)= { nb } is related to Beatty sequences. If b is irrational, it is…Continue
Data science pioneer, founder, author, CEO, investor, with broad spectrum of domain expertise, technical knowledge, and proven success in bringing measurable added value to companies ranging from startups to fortune 100, across multiple industries (finance, Internet, media, IT, security) and domains (data science, operations research, machine learning, computer science, business intelligence, statistics, applied mathematics, growth hacking, IoT).
Vincent developed and deployed new techniques such as hidden decision trees (for scoring and fraud detection), automated tagging, indexing and clustering of large document repositories, black-box, scalable, simple, noise-resistant regression known as the Jackknife Regression (fit for black-box, real-time or automated data processing), model-free confidence intervals, bucketisation, combinatorial feature selection algorithms, detecting causation not correlations, and generally speaking, the invention of a set of consistent robust statistical / machine learning techniques that can be understood, implemented, interpreted, leveraged and fine-tuned by the non-expert. Vincent also invented many synthetic metrics (for instance, predictive power and L1 goodness-of-fit) that work better than old-fashioned stats, especially on badly-behaved sparse big data. Some of these techniques have been implemented in a Map-Reduce Hadoop-like environment. Some are concerned with identifying true signal in an ocean of noisy data.
Vincent is a former post-doctorate of Cambridge University and the National Institute of Statistical Sciences. He was among the finalists at the Wharton School Business Plan Competition and at the Belgian Mathematical Olympiads. Vincent has published 40 papers in statistical journals and is an invited speaker at international conferences. Vincent also created the first IoT platform to automate growth and content generation for digital publishers, using a system of API's for machine-to-machine communications, involving Hootsuite, Twitter, and Google Analytics.
Vincent's profile is accessible at http://bit.ly/1jWEfMP and includes top publications, presentations, and work experience with Visa, Microsoft, eBay, NBC, Wells Fargo, and other organisations.
Dennis Sweitzer replied to Vincent Granville's discussion Simulating Distributions with One-Line Formulas, even in ExcelRaj Singh liked Vincent Granville's blog post Free Book: Deep Learning and Computer Vision with CNNsDennis Sweitzer replied to Vincent Granville's discussion Simulating Distributions with One-Line Formulas, even in ExcelRaj Singh liked Vincent Granville's blog post Comprehensive Repository of Data Science and ML ResourcesDear Vincent,
Do you know how long does membership approval in "Analytic Bridge" take? I want to submit an answer to the self-correcting random walk problem. The answer is long, and I left a copy of my document (not the final draft) in Github.
Dr. Granville,
I enjoyed your white paper on Building Dashboards that Flow and could not agree more with minimalism. One thing that seems to be missing from the dashboard packages I've seen is control charts. At least for the process owner, my personal opinion is a control chart should be the first chart. If the process is not stable and predicable, statistical analysis seems futile. Before I retired (two months ago) we started including these in the process owners' LEAN PIT boards. We generated them in Minitab. It only takes a few clicks once the data is paste into Minitab. Bill Bahl
Dean Pangelinan said… Dr. Granville,
Regarding the passerelle options for the Data Science certification program, does the notation of "IEEE Computer Science Society - Member" refer to Associate Membership in the IEEE Computer Society, or to full IEEE Membership with additional membership in the IEEE Computer Science Society?
Please advise, at your earliest convenience.
-- Dean Pangelinan
Lissy Able said… Hi Vincent,
Can you suggest some points or links about serious data quality issue with the information pulled.
Thanks
Lissy
Vincent,
I recently was hired as a data scientist. As a new hire, leading the department of Business Intelligence, I am faced with self-posed questions such as, "What do I need to accomplish in the first 5 days?" And, "What should I accomplish in the first month?" And, of course, "How do I develop a long-term plan for transforming the business into a data-driven organization?" To make the problem of determining how I should focus my attention even more complicated, I have a single employee whom I want to groom to understand the algorithms that I am implementing. Also, I have a CEO who only agreed to hire for this position because the CIO, CFO, and COO encouraged him to do so, but he is highly skeptical of what data science can do for the organization; this complicates matters too because it puts on me a pressure to be dazzling right out-of-the-box.
I have given these questions considerable thought. I am on day 3 of my new job. I have decided to orient myself on the business' data, query tools, and self-service tools, such as QlikView. I have so many ideas, I have difficulty in choosing a single direction in which I should run. I must note that I want to be significantly impactful while minimizing disruptions in the business' daily functions. To that end, I keep thinking, "run a clustering analysis! Discover the patterns and trends in the company's data to begin the model-building process."
What advice would you give a young data scientist on his 4th day on the job (as it is for me, tomorrow)?
I thought you might like this site: http://rpsychologist.com/d3/CI/
Being from Belgium, you are welcome to join our meetup group about data sciences http://www.meetup.com/Brussels-Data-Science-Community-Meetup/
Posted on November 14, 2019 at 11:00am 0 Comments 0 Likes
Here is our selection of featured articles and technical resources posted since Monday:
Announcements
Technical Resources…
ContinuePosted on November 10, 2019 at 10:30am 0 Comments 0 Likes
If X(1), X(2), ..., X(n) are independent random variables, not necessarily with the same distribution, what is the variance of Z = X(1) X(2) ... X(n)? It turns out that the computation is very simple:
In particular, if all the expectations are zero, then the…
ContinuePosted on November 10, 2019 at 8:30am 0 Comments 0 Likes
Monday newsletter published by Data Science Central. Previous editions can be found here. The contribution flagged with a + is our selection for the picture of the week. To subscribe, follow this link.
Featured Resources and Technical…
ContinuePosted on November 7, 2019 at 12:30pm 0 Comments 0 Likes
Here is our selection of featured articles and technical resources posted since Monday:
Announcements
Resources…
Continue
© 2019 Data Science Central ®
Powered by
Badges | Report an Issue | Privacy Policy | Terms of Service
