DataRobot Blog

APRIL 29, 2022

Prior to the financial crisis of 2008, Model Risk Management within the financial services industry was driven by industry best practices rather than regulatory standards(which brings to mind the saying “a fox guarding the hen house”). The regulators have provided a universal definition that has been adopted across the financial industry.

Risk 111

Risk Modeling IT Risk Management 111

DataRobot

AUGUST 3, 2021

They’re statistical methods of leveraging data. That is what led Joshua to found Lex Machina in 2008. That’s something we can grapple with, and that doesn’t terrify people. One reason people like the terms machine learning or neural networks is that they’re more specific.

Informatics 52

Informatics Statistics Machine Learning Software 52

Alation

FEBRUARY 20, 2020

Metrics and statistics are wonderful, but we need to surround data with more context and lower the costs of using data. For those of us who champion the power of data, the past five years have been an incredible ride thanks to the rise of big data.

Big Data 52

Big Data Data-driven Statistics Metrics 52

The Unofficial Google Data Science Blog

APRIL 17, 2017

An obvious requisite property of reconciliation is arithmetic coherence across the hierarchy (which is implicit in the sum-up-from-the-bottom possibility in the previous paragraph), but more sophisticated reconciliation may induce statistical stability of the constituent forecasts and improve forecast accuracy across the hierarchy.

Forecasting 83

Forecasting Modeling Statistics Uncertainty 83

bridgei2i

MAY 26, 2020

You know the markets shake and the accompanying Swine Flu epidemic of 2015 and 2016, the Japanese tsunami and the Thailand floods in 2011 that shook up the high-tech value chain quite a bit, the great financial crisis and the accompanying H1N1 outbreak in 2008-2009, MERS and SARS before that in 2003.

Enterprise 131

Enterprise Management Forecasting Manufacturing 131

Peter James Thomas

JUNE 20, 2019

Of course it can be argued that you can use statistics (and Google Trends in particular) to prove anything [1] , but I found the above figures striking. Feel free to substitute Data Lake for Data Warehouse if you want a more modern vibe, sadly it won’t change the failure statistics. . [5]. Source: Google Trends.

Cost-Benefit 55

Cost-Benefit Data Warehouse Consulting Data Science 55

O'Reilly on Data

MAY 27, 2020

So the state calculates and publishes a “Risk Adjusted Mortality Ratio”—a comparison between the actual number of observed deaths and the number that would be statistically expected, on average, for patients medically similar to those each doctor actually operated on.

Risk 355

Risk Testing Reporting Measurement 355

O'Reilly on Data

JULY 15, 2019

After the 2008 financial crisis, the Federal Reserve issued a new set of guidelines governing models— SR 11-7 : Guidance on Model Risk Management. In our experience, many of the most popular conference talks on model explainability and interpretability are those given by speakers from finance. Image by Ben Lorica. Sources of model risk.

Machine Learning 38

Machine Learning Management Enterprise Risk Management 38

DataKitchen

MAY 10, 2021

Since 2008, teams working for our founding team and our customers have delivered 100s of millions of data sets, dashboards, and models with almost no errors. We liken this methodology to the statistical process controls advocated by management guru Dr. Edward Deming. Statistical Process Control. Focus on the process.

Testing 214

Testing Manufacturing Data Quality Statistics 214

Data Science and Beyond

JULY 22, 2018

Two years later, I published a post on my then-favourite definition of data science , as the intersection between software engineering and statistics. Like other authors, they argue that causal inference has been neglected by traditional statistics and some scientific disciplines. In a recent article , Hernán et al.

Data Science 79

Data Science Machine Learning Statistics Predictive Modeling 79

Domino Data Lab

JULY 22, 2019

He was saying this doesn’t belong just in statistics. It involved a lot of work with applied math, some depth in statistics and visualization, and also a lot of communication skills. Tukey did this paper. It’s a great read. It is 50, almost 60 years ago, but he was talking about something that was interdisciplinary.

Data Science 109

Data Science Machine Learning Data Governance Modeling 109

Domino Data Lab

JANUARY 6, 2019

I’ve been teaching data science since 2008 privately for employers – exec staff, investors, IT teams, and the data teams I’ve led – and since 2013, for industry professionals in general. Lately I’ve been developing curriculum for a client for their new “Intro to Data Science” sequence of courses. This is not a new gig, by any stretch.

Data Science 56

Data Science Machine Learning Reporting Visualization 56

The Unofficial Google Data Science Blog

JULY 11, 2017

SCOTT Time series data are everywhere, but time series modeling is a fairly specialized area within statistics and data science. They may contain parameters in the statistical sense, but often they simply contain strategically placed 0's and 1's indicating which bits of $alpha_t$ are relevant for a particular computation. by STEVEN L.

Forecasting 64

Forecasting Statistics Modeling Software 64

Domino Data Lab

AUGUST 8, 2019

2008 – Financial crisis : scientists flee Wall St. Another key point: troubleshooting edge cases for models in production—which is often where ethics and data meet, as far as regulators are concerned—requires much more sophistication in statistics than most data science teams tend to have. It’s a quick way to clear the room.

Data Science 71

Data Science Machine Learning Data Governance Statistics 71

Occam's Razor

SEPTEMBER 29, 2009

Use tools like Google Trends for Websites (or Compete or HitWise ) to analyze your performance… In the report above if you ( Hilton Hotels ) ran your campaigns in March 2008 (purple arrow) then you managed to accomplish nothing. Notice the competitive trends? The data on the right is killer.

Measurement 128

Measurement Metrics Analytics Marketing 128

datapine

NOVEMBER 19, 2019

Currently, popular approaches include statistical methods, computational intelligence, and traditional symbolic AI. Blockchain was invented in 2008 to serve as a ledger of the cryptocurrency bitcoin. Depending on the circles you run in, bitcoin was either: The shadiest thing that has ever happened to the internet.

Technology 279

Technology Internet of Things IT IoT 279

The Unofficial Google Data Science Blog

SEPTEMBER 30, 2016

The statistics app for Google Sheets hopes to change that. Editor's note: We've mostly portrayed data science as statistical methods and analysis approaches based on big data. Introduction Statistics for Google Sheets is an add-on for Google Sheets that brings elementary statistical analysis tools to spreadsheet users.

Statistics 53

Statistics Big Data Data Science Marketing 53

Domino Data Lab

AUGUST 22, 2019

Although it’s not perfect, [Note: These are statistical approximations, of course!] representations using RNN encoder-decoder for statistical machine translation. Example 11.6 Detecting collocated bigrams with more conservative thresholds. lower_bigram = Phraser(Phrases(lower_sents, min_count=32, threshold=64)). Example 11.9

Deep Learning 111

Deep Learning Modeling Metrics Testing 111

Domino Data Lab

MARCH 27, 2019

Select all rows from the 2008 election. votes_2008 <- filter(presidentialElections, year == 2008). The preceding filter() statement is equivalent to extracting the rows using the following base R syntax: # Select all rows from the 2008 election. votes_2008 <- presidentialElections[presidentialElections$year == 2008, ].

Statistics 85

Statistics Data Science Visualization IT 85

O'Reilly on Data

JANUARY 25, 2021

in 2008 and continuing with Java 8 in 2014, programming languages have added higher-order functions (lambdas) and other “functional” features. Healthy growth in artificial intelligence has continued: machine learning is up 14%, while AI is up 64%; data science is up 16%, and statistics is up 47%. Starting with Python 3.0

Machine Learning 363

Machine Learning Software Testing Technology 363

Jet Global

APRIL 5, 2021

For example, pension funds must be able to pay pensioners during any economic conditions, including a crisis like 2008. These financial models are used to assign a price (premium) for the options contract based on statistics and probability (i.e. Most pension funds conduct a comprehensive review every three to five years.

Modeling 98

Modeling Forecasting Metrics Finance 98