그 동안 머신러닝 해석력 시리즈를 통해서 머신러닝의 부분 의존성(PD; Partial Dependence), 데이터 세트 해석 등을 소개해드렸는데요. 오늘은 라임(LIME; Local Interpretable Model-Agnostic Explanation)을 통해 머신러닝 모델의 해석력을 개선할 수 있는 방법에 대해서 알아보겠습니다. 머신러닝 모델 해석력 시리즈 1탄, 2탄, 3탄을 놓치셨다면 아래 링크를 통해 확인해주세요! 머신러닝 해석력 시리즈 1탄: 인공지능(AI)과 머신러닝을 신뢰하기 위한 필수
The best way to spread Christmas cheer is singing loud for all to hear! -Buddy in Elf In the Christmas movie Elf (2003), Jovie (played by Zooey Deschanel) must "spread Christmas cheer" to help Santa. She chooses to sing "Santa Claus is coming to town," and soon all of New
Once again, I have chosen to take a traditional Christmas song or carol and create a fun technology-related version of it to share with you. This is the fifth year and the eighth song, so I hope you enjoy your 2018 holiday song. Grandma got over run by a neural
Phil Simon chimes in on the increasingly important topic of data literacy.
There is one equation every retail store, call center, traffic, airport or hospital manager should know by heart. No, it’s not E = mc². The one I had in mind is this: W = 1 / (μ – λ) It may not look like much, but it can mean the
After almost 32 years, I am retiring from SAS.
Joseph Woodside discusses the use of using ensemble modeling in SAS for fraud detection and readmissions.
Creative government workforce approaches come in many forms. Some time ago, the US Environmental Protection Agency (EPA) offered employees an interesting choice to incentivize them to stay. Employees could either telework from home one day per week or receive $1,000. As Jon Lemon, principal industry consultant at SAS told the
Recently a SAS programmer wanted to obtain a table of counts that was based on a histogram. I showed him how you can use the OUTHIST= option on the HISTOGRAM statement in PROC UNIVARIATE to obtain that information. For example, the following call to PROC UNIVARIATE creates a histogram for
It might snow this weekend here at the SAS headquarters! This would be the first snow of the season for us, and it got me thinking about snow again (see some of my previous blog posts about snow). Apparently these thoughts have manifested themselves in my computer graphics work ...
Find out how to kick-start your volunteering and leadership skills at SAS Global Forum.
Nicht erst im Zeitalter von künstlicher Intelligenz (KI) und Real-Time Decision Engines werden historische und aktuelle Verhaltensweisen von Kunden analysiert. Die Praxis, anhand dieser Informationen Entscheidungen zu treffen und sie in Echtzeit auf die Kundeninteraktion anzuwenden, gab es bereits in den 1970er-Jahren. Frau Cerny betrieb den Lebensmittelladen im Wohnhaus meiner
Ich muss gestehen: ich bin leidenschaftlicher Gamer. Man könnte auch sagen, ein „Nerd“. Ich liebe Computerspiele, nicht nur, sie zu spielen, sondern ich möchte auch wissen, wie sie gemacht werden, wie sie funktionieren und wohin die Entwicklung in Zukunft führen wird. Ganz besonders interessiert mich, wie künstliche Intelligenz in Spielen
In this blog series, we’ve spoken directly to professors to find out why it’s so important to teach analytics, their advice for students, and to learn how they create interest in analytics programs at their universities. For this third and final post, we’ll hear how SAS has played a role
A conversation with my mentor has always stuck in my mind: Teaching is not about me, directly, it’s about serving my students. Teaching is about providing each of my students what they need to learn the material and to grow academically and as an individual. Teaching is about student learning.
Data scientists need good skills in communication, data mining, data wrangling and more. Joyce Norris-Montanari explains.
When a graph includes several markers or line styles, it is often useful to create a legend that explains the relationship between the data and the symbols, color, and line styles in the graph. The SGPLOT procedure does a good job of automatically creating and placing a legend for most
머신러닝의 블랙 박스 모델을 소개하는 첫 번째 블로그와 두 번째 블로그를 통해서 머신러닝 모델의 복잡성과 머신러닝의 뛰어난 예측 결과를 활용할 수 있는 해석력이 필요한 이유, 적용 분야에 대해서 소개해드렸는데요. 이번에는 기업 실무자 입장에서 SAS 비주얼 데이터 마이닝 앤드 머신러닝(SAS Visual Data Mining and Machine Learning)을 활용한 SAS 커스터머 인텔리전스 360(SAS Customer Intelligence 360)에서 해석 기법과
Whether you're reading industry articles about smart tags or analyst reports about inventory tracking, you've probably noticed an uptick in coverage on the adoption of IoT (and RFID) in retail. Since I've been following these topics for awhile, I've decided to dedicate a series of posts on the ways IoT can be used
In August 2018, Hurricane Florence came on shore in North Carolina. Much of the damage was from flooding because the storm moved slowly over North and South Carolina. Parts of North Carolina had over 30 inches of rain from the storm, and this caused many of North Carolina’s rivers to
La prova definitiva per poter definire una tecnologia “mainstream” consiste nel verificare che essa venga ampiamente utilizzata in tutta l'azienda, dalle funzioni a servizio del cliente alle attività di back-office. Gli analytics sono stati a lungo incentrati sul cliente ed ampiamente utilizzati anche per le prestazioni individuali, ad esempio, dalle
Find out what SAS Global Forum 2019 conference chair MaryAnne DePesquo says about the upcoming conference in Dallas.
I first used telemedicine (the remote diagnosis and treatment of patients by means of telecommunications technology) in the mid-90s when I was working as an on-call CT technician in the UK. We used a modem to transfer head trauma scans to the local neurology center for assessment so that the
The opioid epidemic continues to be one of the largest challenges facing the United States. In 2016, more than 42,000 Americans died from opioid overdoses, and that number continues to climb. Recent data shows that more than 130 people die every day in the United States after overdosing on opioids,
I remember the first time I used PROC GLM in SAS to include a classification effect in a regression model. I thought I had done something wrong because the parameter estimates table was followed by a scary-looking note: Note: The X'X matrix has been found to be singular, and a
Jim Harris says data stewards are essential to analytics, providing life cycle management for data across the enterprise.
초강력 허리케인 '플로렌스’ 미국 남동부 지역을 강타하다 지난 9월, 대서양에서 발생한 초강력 허리케인 '플로렌스(Florence)'가 미국 노스캐롤라이나주를 비롯한 미국 남동부 지역을 강타했습니다. 하루 무려에 762mm 기록적 물폭탄이 내리면서 허리케인으로 인한 재산 피해액은 총 170~220억달러(약 19조~25조원) 인것으로 추정되기도 했는데요. 허리케인 플로렌스가 쓸고 간 자리에는 집, 일자리, 건물, 학교 등을 잃은 이재민들이 남았습니다.
지난 'SAS 커스터머 인텔리전스 360(SAS Customer Intelligence 360): 머신러닝의 블랙 박스 모델이란’ 블로그에서 머신러닝 모델은 다면적이고 계속 진화하는 주제라고 소개해드린 바 있는데요. 오늘은 머신러닝 모델의 해석력(Interpretability)에 대해 자세히 살펴보고자 합니다. 머신러닝 모델은 놀라운 예측 능력을 제공하지만 매우 복잡하여 이해하기 쉽지 않습니다. 또한 머신러닝 모델은 예측한 결과에 대한 명확한 설명도 제공하지 않기
Do you remember The Matrix movies, that started coming out in 1999? Hopefully this movie franchise didn't give you a fear of virtual reality and AI. The thing I remember most from the movie was the really cool slow-motion video effects (from multiple angles) in the fight scenes. And the
As analíticas vão ser imprescindíveis no futuro. Está é a opinião generalizada da maioria dos gestores. No entanto um estudo levado a cabo pelo SAS sobre Plataforma Analítica - “Here and Now: the need for an analytics platform”, revelou que apenas 35% está efectivamente com projectos de implementação ao nível
