Marc Stein, Underwrite.ai - Driverless AI Use Cases in Finance and Cancer Genomics - H2O World SF

•Als PPTX, PDF herunterladen•

1 gefällt mir•470 views

This session was recorded in San Francisco on February 9th, 2019 and can be viewed here: https://youtu.be/6KY4CSA1AzU Marc Stein is the founder and CEO of Underwrite.ai. Underwrite.ai applies advances in artificial intelligence derived from genomics and particle physics to provide lenders with non-linear, dynamic models of credit risk which radically outperform traditional approaches. Marc’s career has always revolved around deep interests in artificial intelligence, quantum physics, genomics, sugar cream pie, and all ice cream flavors found at Berthillon and the challenge of how to combine all these in practical applications.

Technologie

Linear vs Nonlinear
Credit Modeling
Marc Stein
Founder and CEO
Underwrite.ai
#H2OWORLD

Korean Credit Market
• Highly efficient credit system
• Very low default rate and commensurately low interest rates

This is a logistic regression model based upon four key attribute areas.
How Credit Grade is Derived

Efficiency of Current Model
Credit Grade AUC = 0.90640

Efficiency of Current Model
This is a logistic regression model that
works very well. It utilizes a small
feature set very efficiently. This linear
model is quite performant.

Nonlinear Approach
But what if we take a nonlinear
approach and use H20 and DAI to
model the problem?

Nonlinear Approach
Are there gains to be had by using 763
variables in a combinatorial manner in
place of the linear model?

Nonlinear Approach
Experiment: CDS3, 2018-12-19 00:04, 1.4.2
Settings: 8/5/5, seed=828672342, GPUs enabled
Train data: CDS3_SELECTED Training.csv (60000, 67)
Validation data: CDS3_Selected Validate.csv (30000, 67)
Test data: CDS3_Selected Hold.csv (10000, 66)
Target column: outcome (binary, 99.258% target class)
System specs: Docker/Linux, 16 GB, 4 CPU cores, 1/1 GPU
Max memory usage: 2.98 GB, 0.595 GB GPU
Recipe: AutoDL (98 iterations, 8 individuals)
Validation scheme: user-given validation data
Feature engineering: 16749 features tested (210 selected)
Timing:
Data preparation: 8.89 secs
Model and feature tuning: 640.33 secs (49 models trained)
Feature evolution: 3085.32 secs (397 models trained)
Final pipeline training: 148.83 secs (1 model trained)
Validation score: AUC = 0.94953 +/- 0.0026775 (baseline)
Validation score: AUC = 0.95162 +/- 0.0026263 (final pipeline)
Test score: AUC = 0.95813 +/- 0.0072649 (final pipeline)

Efficiency of Current Model vs DAI Model
Credit Grade AUC = 0.90640
DAI AUC = 0.95813

Take Away
A highly efficient logistic regression model can
be significantly outperformed by a GBM model
which incorporates more data.

Less Efficient Models
US Case Study
Large consumer lender with an overall
bad loan rate of 8.6%

Marc Stein, Underwrite.ai - Driverless AI Use Cases in Finance and Cancer Genomics - H2O World SF

Weitere ähnliche Inhalte

Was ist angesagt?

Machine Learning with H2O

Sri Ambati

This talk was recorded in London on Oct 30, 2018 and can be viewed here: https://youtu.be/p4iAnxwC_Eg The good news is building fair, accountable, and transparent machine learning systems is possible. The bad news is it’s harder than many blogs and software package docs would have you believe. The truth is nearly all interpretable machine learning techniques generate approximate explanations, that the fields of eXplainable AI (XAI) and Fairness, Accountability, and Transparency in Machine Learning (FAT/ML) are very new, and that few best practices have been widely agreed upon. This combination can lead to some ugly outcomes! This talk aims to make your interpretable machine learning project a success by describing fundamental technical challenges you will face in building an interpretable machine learning system, defining the real-world value proposition of approximate explanations for exact models, and then outlining the following viable techniques for debugging, explaining, and testing machine learning models Mateusz is a software developer who loves all things distributed, machine learning and hates buzzwords. His favourite hobby data juggling. He obtained his M.Sc. in Computer Science from AGH UST in Krakow, Poland, during which he did an exchange at L’ECE Paris in France and worked on distributed flight booking systems. After graduation he move to Tokyo to work as a researcher at Fujitsu Laboratories on machine learning and NLP projects, where he is still currently based.

Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018

Sri Ambati

No more grid search! How to build models effectively by Thomas Huijskens

Sri Ambati

This session was recorded in San Francisco on February 5th, 2019 and can be viewed here: https://youtu.be/LUwMtXM2q88 In the current world of data science there many available data sources, big data platforms, and advanced Machine Learning and AI based technologies available. It has become easier and easier to derive predictive value in an efficient and streamlined way and lose sight of objectives especially in the business world. This session will focus on not losing the business context and objective as the navigator for these powerful tools we have at our disposal. Through this discussion, I will review a path towards how to use the tools like explainable and driverless AI to your advantage versus letting the tools set the direction. Bio: At Equifax, Tom leads the Data and Analytics consulting practice. Previously, Tom was the US Consumer and Commercial Data Sciences Leader. Tom joined Equifax in July of 2009. He brings several years of analytical experience in leading teams on statistical modeling engagements, analysis and consultation across several verticals including telecommunications, lending, mortgage, automotive, and marketing. Prior to Equifax, Tom was a data science manager at Experian and a Risk Modeler/Manager at American General Finance (now OneMain Financial). Tom holds a Master of Science in Applied Statistics from Purdue University, and a Bachelor of Science degree in Mathematics with a concentration in Statistics, also from Purdue University.

Tom Aliff, Equifax - Configurable Modeling for Maximizing Business Value - H2...

Sri Ambati

Introduction & Hands-on with H2O Driverless AI

Sri Ambati

Machine Learning Model Deployment and Scoring on the Edge with Automatic Machine Learning and Data Flow YouTube Video URL: https://youtu.be/gB0bTH-L6DE Deploying Machine Learning models to the edge can present significant ML/IoT challenges centered around the need for low latency and accurate scoring on minimal resource environments. H2O.ai's Driverless AI AutoML and Cloudera Data Flow work nicely together to solve this challenge. Driverless AI automates the building of accurate Machine Learning models, which are deployed as light footprint and low latency Java or C++ artifacts, also known as a MOJO (Model Optimized). And Cloudera Data Flow leverage Apache NiFi that offers an innovative data flow framework to host MOJOs to make predictions on data moving on the edge.

ML Model Deployment and Scoring on the Edge with Automatic ML & DF

Sri Ambati

Building, managing, and maintaining thousands of features across thousands of models. Building features can be repetitive, tedious and extremely challenging to scale. We will explore the ‘Feature Factory’ built at Databricks and implemented at several clients and the processes that are imperative for the democratization of feature development and deployment. The feature factory allows consumers to ensure repetitive feature creation, simplifies scoring and enables massive scalability through feature multiplication.

Building A Feature Factory

Databricks

This session was recorded in San Francisco on February 5th, 2019 and can be viewed here: https://youtu.be/diMSemHRNDw This presentation illustrates how to combine innovations from several sub-disciplines of machine learning research to train understandable, fair, trustable, and accurate predictive modeling systems. Techniques from research into fair models, directly interpretable Bayesian or constrained machine learning models, and post-hoc explanations can be used to train transparent, fair, and accurate models and make nearly every aspect of their behavior understandable and accountable to human users. Additional techniques from fairness research can be used to check for sociological bias in model predictions and to preprocess data and post-process predictions to ensure the fairness of predictive models. Finally, applying new testing and debugging techniques, often inspired by best practices in software engineering, can increase the trustworthiness of model predictions on unseen data. Together these techniques create a new and truly human-friendly type of machine learning suitable for use in business- and life-critical decision support. Patrick Hall is senior director for data science products at H2O.ai where he focuses mainly on model interpretability. Patrick is also currently an adjunct professor in the Department of Decision Sciences at George Washington University, where he teaches graduate classes in data mining and machine learning. Prior to joining H2O.ai, Patrick held global customer facing roles and research and development roles at SAS Institute.

Patrick Hall, H2O.ai - Human Friendly Machine Learning - H2O World San Francisco

Sri Ambati

This session was recorded in San Francisco on February 5th, 2019 and can be viewed here: https://youtu.be/f4b2Yoe9JEs Combining H2O Driverless AI, H2O-3, and AWS for developing and deploying AI solutions on scale. Martin Stein is a seasoned Product and Marketing executive with a successful track record delivering large-scale advanced analytics and marketing analytics services and products. Martin has served as Board Member, C-Level Executive and subject matter expert in a variety of industries (Marketing, Finance, Real Estate and Media). Currently, Martin as Chief Analytics Officer for g5, a leader in real estate marketing optimization. G5 is a predictive marketing SaaS company that uses AI and other emerging technologies to help marketers amplify their impact.

Martin Stein, G5 - Driving Marketing Performance with H2O Driverless AI - H2O...

Sri Ambati

Presented at #H2OWorld 2017 in Mountain View, CA. Learn more about H2O.ai: https://www.h2o.ai/. Follow @h2oai: https://twitter.com/h2oai. - - - Effective volume anomaly detection presents unique challenges when monitoring customer transaction volumes across thousands of platforms and systems. We overcome this by using H2O, building on open source tools, and delivering machine learning anomaly detection for enterprise scale. Hear how we model, visualize then automatically alert on anomalous Mobile app volumes in real-time. Donald Gennetten has over 15 years experience supporting digital channels in the Financial Services industry. In his current role as a Data Engineer for Capital One’s Monitoring Intelligence team, he leads a cross-functional group of Data, Business, and Engineering subject matter experts to deliver Advanced Analytics solutions for real-time customer transaction monitoring and issue detection. Rahul Gupta is a Data Engineer in Capital One's Center for Machine Learning, focusing heavily on back-end development and model creation. His primary efforts include building an Algorithmic IT Operations (AIOps) platform that utilizes a combination of batch and streaming data with Machine Learning capabilities to improve the stability of Capital One services and overall customer experience.

Using H2O for Mobile Transaction Forecasting & Anomaly Detection - Capital One

Sri Ambati

In this presentation, Parul Pandey, will provide a history and overview of the field of “Automatic Machine Learning” (AutoML), followed by a detailed look inside H2O’s open source AutoML algorithm. H2O AutoML provides an easy-to-use interface which automates data pre-processing, training and tuning a large selection of candidate models (including multiple stacked ensemble models for superior model performance). The result of the AutoML run is a “leaderboard” of H2O models which can be easily exported for use in production. AutoML is available in all H2O interfaces (R, Python, Scala, web GUI) and due to the distributed nature of the H2O platform, can scale to very large datasets. The presentation will end with a demo of H2O AutoML in R and Python, including a handful of code examples to get you started using automatic machine learning on your own projects. Parul's Bio: Parul is a Data Science Evangelist here at H2O.ai. She combines Data Science, evangelism and community in her work. Her emphasis is to spread the information about H2O and Driverless AI to as many people as possible, She is also an active writer and has contributed towards various national and international publications.

Scalable Automatic Machine Learning with H2O

Sri Ambati

This presentation was made on June 18, 2020. Video recording of the session can be viewed here: https://youtu.be/YEtDwYSXXJo For many companies, model documentation is a requirement for any model to be used in the business. For other companies, model documentation is part of a data science team’s best practices. Model documentation includes how a model was created, training and test data characteristics, what alternatives were considered, how the model was evaluated, and information on model performance. Collecting and documenting this information can take a data scientist days to complete for each model. The model document needs to be comprehensive and consistent across various projects. The process of creating this documentation is tedious for the data scientist and wasteful for the business because the data scientist could be using that time to build additional models and create more value. Inconsistent or inaccurate model documentation can be an issue for model validation, governance, and regulatory compliance. In this virtual meetup, we will learn how to create comprehensive, high-quality model documentation in minutes that saves time, increases productivity, and improves model governance. Speaker's Bio: Nikhil Shekhar: Nikhil is a Machine Learning Engineer at H2O.ai. He is currently working on our automatic machine learning platform, Driverless AI. He graduated from the University of Buffalo majoring in Artificial Intelligence and is interested in developing scalable machine learning algorithms.

Automatic Model Documentation with H2O

Sri Ambati

Material for Azure Machine Learning tutorial lecture, held within Data Mining course of MoS in Engineering in Computer Science at Università degli Studi di Roma "La Sapienza" (A.Y. 2016/2017). Lecturers: Fabio Rosato - rosato.1565173@studenti.uniroma1.it Giacomo Lanciano - lanciano.1487019@studenti.uniroma1.it Francisco Ferreres Garcia - matakukos@gmail.com Leonardo Martini - martini.1722989@studenti.uniroma1.it Simone Caldaro - caldaro.1324152@studenti.uniroma1.it Na Zhu - nana.zhu@hotmail.com Github repo: https://github.com/giacomolanciano/Azure-Machine-Learning-tutorial Video tutorial: https://youtu.be/_zvPX6Kk7z8

Azure Machine Learning tutorial

Giacomo Lanciano

Building Understanding Out of Incomplete and Biased Datasets using Machine Le...

Databricks

Presented at #H2OWorld 2017 in Mountain View, CA. Enjoy the video: https://youtu.be/-rGRHrED94Y. Learn more about H2O.ai: https://www.h2o.ai/. Follow @h2oai: https://twitter.com/h2oai. - - - Abstract: Most machine learning systems enable two essential processes: creating a model and applying the model in a repeatable and controlled fashion. These two processes are interrelated and pose technological and organizational challenges as they evolve from research to prototype to production. This presentation outlines common design patterns for tackling such challenges while implementing machine learning in a production environment. Sergei's Bio: Dr. Sergei Izrailev is Chief Data Scientist at BeeswaxIO, where he is responsible for data strategy and building AI applications powering the next generation of real-time bidding technology. Before Beeswax, Sergei led data science teams at Integral Ad Science and Collective, where he focused on architecture, development and scaling of data science based advertising technology products. Prior to advertising, Sergei was a quant/trader and developed trading strategies and portfolio optimization methodologies. Previously, he worked as a senior scientist at Johnson & Johnson, where he developed intelligent tools for structure-based drug discovery. Sergei holds a Ph.D. in Physics and Master of Computer Science degrees from the University of Illinois at Urbana-Champaign.

Design Patterns for Machine Learning in Production - Sergei Izrailev, Chief D...

Sri Ambati

Big Wins with Small Data: PredictionIO in Ecommerce

David Jones

This session was recorded in San Francisco on February 5th, 2019 and can be viewed here: https://youtu.be/4a_Y0L7suBc AI is real. Enterprises use it to automate decisions, hyper-personalize customer experiences, streamline operational processes, and much more. However, for most enterprise technology leaders, AI technologies and use cases are still far too mysterious. The field is moving fast. Enterprise leaders must forge a coherent, pragmatic AI strategy that is tied to business outcomes. In this session, guest speaker Forrester Research Vice President & Principal Analyst Mike Gualtieri will demystify enterprise AI, identify use cases most likely to succeed, and, most importantly, provide key advice to enterprise leaders that are charged with moving AI forward in their organization. Bio: Mike's research focuses on software technologies, platforms, and practices that enable technology professionals to deliver digital transformations that lead to prescient digital experiences and breakthrough operational efficiency. His key technology coverage areas are AI, machine learning, deep learning, AI chips and systems, digital decisions, streaming analytics, prescriptive analytics, big data analytical platforms and tools (Hadoop/Spark/Flink; translytical databases), optimization, and emerging technologies that make software faster and smarter. Mike is also a leading expert on the intersection of business strategy, artificial intelligence, and innovation. Mike provides technology vendors with actionable, fine-tuned advisory sessions on strategy, messaging, competitive analysis, buyer-persona analysis, market trends, and product road maps for the areas he directly covers and adjacent areas that wish to launch into new markets or use new technologies. Mike is a recipient of the Forrester Courage Award for making bold calls that inspire leaders and guide great business and technology decisions.

Keynote by Mike Gualtieri, Forrester Research - Making AI Happen Without Gett...

Sri Ambati

Custom Machine Learning Recipes

Sri Ambati

The session is about creating, training, evaluating and deploying machine learning with no-code approach using Azure AutoML. * NO MACHINE LEARNING EXPERIENCE REQUIRED * Agenda: 1. Introduction to Machine Learning 2. What is AutoML (Automated Machine Learning) ? 3. AutoML versus Conventional ML practices 4. Intro to Azure Automated Machine Learning 5. Hands-on demo 6 Contest 6. Learning resources 7. Conclusion

Getting Started with Azure AutoML

Vivek Raja P S

TensorFlow 16: Building a Data Science Platform

Seldon

Was ist angesagt? (20)

Machine Learning with H2O

Machine Learning Interpretability - Mateusz Dymczyk - H2O AI World London 2018

No more grid search! How to build models effectively by Thomas Huijskens

Tom Aliff, Equifax - Configurable Modeling for Maximizing Business Value - H2...

Introduction & Hands-on with H2O Driverless AI

ML Model Deployment and Scoring on the Edge with Automatic ML & DF

Building A Feature Factory

Patrick Hall, H2O.ai - Human Friendly Machine Learning - H2O World San Francisco

Martin Stein, G5 - Driving Marketing Performance with H2O Driverless AI - H2O...

Using H2O for Mobile Transaction Forecasting & Anomaly Detection - Capital One

Scalable Automatic Machine Learning with H2O

Automatic Model Documentation with H2O

Azure Machine Learning tutorial

Building Understanding Out of Incomplete and Biased Datasets using Machine Le...

Design Patterns for Machine Learning in Production - Sergei Izrailev, Chief D...

Big Wins with Small Data: PredictionIO in Ecommerce

Keynote by Mike Gualtieri, Forrester Research - Making AI Happen Without Gett...

Custom Machine Learning Recipes

Getting Started with Azure AutoML

TensorFlow 16: Building a Data Science Platform

Ähnlich wie Marc Stein, Underwrite.ai - Driverless AI Use Cases in Finance and Cancer Genomics - H2O World SF

Customer choice probabilities

Allan D. Butler

Using Bayesian Optimization to Tune Machine Learning Models

Scott Clark

Using Bayesian Optimization to Tune Machine Learning Models

SigOpt

Meetup_Consumer_Credit_Default_Vers_2_All

Bernard Ong

Supply chain design and operation

AngelainBay

Six sigma11

Jitesh Gaurav

machineLearningTypingTool_Rev1

Bryan Butler, MBA, MS

Using Bayesian Optimization to Tune Machine Learning Models: In this talk we briefly introduce Bayesian Global Optimization as an efficient way to optimize machine learning model parameters, especially when evaluating different parameters is time-consuming or expensive. We will motivate the problem and give example applications. We will also talk about our development of a robust benchmark suite for our algorithms including test selection, metric design, infrastructure architecture, visualization, and comparison to other standard and open source methods. We will discuss how this evaluation framework empowers our research engineers to confidently and quickly make changes to our core optimization engine. We will end with an in-depth example of using these methods to tune the features and hyperparameters of a real world problem and give several real world applications.

Scott Clark, Co-Founder and CEO, SigOpt at MLconf SF 2016

MLconf

MLConf 2016 SigOpt Talk by Scott Clark

SigOpt

Marketing Analytics RM Report

CSCCIX2005

Six sigma & TQM

Six Sigma-s04.ppt

Six Sigma-s04.ppt

six sigma-s04.ppt

Development of calibrated operational models of existing buildings for real-t...

IES VE

Presented at CIBSE Technical Symposium 2016, April 14-15, Heriot Watt Uni, Edinburgh Full paper available here: https://www.researchgate.net/publication/301621663_Development_of_Calibrated_Operational_Models_of_Existing_Buildings_for_Real-Time_Decision_Support_and_Performance_Optimisation Building simulation tools are commonly used in design for performance appraisal and optimisation. However, numerous studies have found that actual building performance often deviates significantly from simulation predictions. This paper proposes a detailed framework to produce calibrated operational models, which can support operational decision-making, and real-time control optimisation. The approach centres around a three-tier calibration process: Tier 1 focuses on Building-level (Demand-side) variables (e.g. occupancy, equipment, infiltration). Tier 2 focuses on system-level (HVAC) model components (e.g. heating / cooling coil capacities). In this phase, we use detailed building data combined with genetic optimisation techniques to calibrate relevant input parameters. In the case where system performance modelling is not necessary, we use free-form profiles (i.e. measured building data) to supplement these model components. Once system-level noise has been eliminated, in Tier 3 we calibrate the remaining plant-level parameters (e.g. central plant, electricity consumption, etc.). The approach is supported by two novel developments: (1) Free-form profiles: These are actual historic trends from existing building controllers, which are used to supplement model components where appropriate; (2) Genetic Optimisation algorithms are utilised to efficiently navigate the solution space to reduce discrepancies between the model and actual system performance. The proposed calibration approach builds upon prior research efforts to standardise the calibration process using evidence-based model development, combined with sensitivity and uncertainty analysis.

Development of Calibrated Operational Models for Real-Time Decision Support a...

Daniel Coakley

6 sigma

Ahsan Saleem

Quality andc apability hand out 091123200010 Phpapp01

jasonhian

SigOpt for Machine Learning and AI

SigOpt

Ähnlich wie Marc Stein, Underwrite.ai - Driverless AI Use Cases in Finance and Cancer Genomics - H2O World SF (20)

Customer choice probabilities

Using Bayesian Optimization to Tune Machine Learning Models

Meetup_Consumer_Credit_Default_Vers_2_All

Supply chain design and operation

Six sigma11

machineLearningTypingTool_Rev1

Scott Clark, Co-Founder and CEO, SigOpt at MLconf SF 2016

MLConf 2016 SigOpt Talk by Scott Clark

Marketing Analytics RM Report

CSCCIX2005

Six sigma & TQM

Six Sigma-s04.ppt

six sigma-s04.ppt

Development of calibrated operational models of existing buildings for real-t...

Development of Calibrated Operational Models for Real-Time Decision Support a...

6 sigma

Quality andc apability hand out 091123200010 Phpapp01

SigOpt for Machine Learning and AI

Mehr von Sri Ambati

H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day

Sri Ambati

Generative AI Masterclass - Model Risk Management.pptx

Sri Ambati

AI and the Future of Software Development: A Sneak Peek

Sri Ambati

LLMOps: Match report from the top of the 5th

Sri Ambati

Building, Evaluating, and Optimizing your RAG App for Production

Sri Ambati

Sandeep Singh, Head of Applied AI Computer Vision, Beans.ai H2O Open Source GenAI World SF 2023 In the modern era of machine learning, leveraging both open-source and closed-source solutions has become paramount for achieving cutting-edge results. This talk delves into the intricacies of seamlessly integrating open-source Large Language Model (LLM) solutions like Vicuna, Falcon, and Llama with industry giants such as ChatGPT and Google's Palm. As the demand for fine-tuned and specialized datasets grows, it is imperative to understand the synergy between these tools. Attendees will gain insights into best practices for building and enriching datasets tailored for fine-tuning tasks, ensuring that their LLM projects are both robust and efficient. Through real-world examples and hands-on demonstrations, this talk will equip attendees with the knowledge to harness the power of both open and closed-source tools in a coherent and effective manner.

Building LLM Solutions using Open Source and Closed Source Solutions in Coher...

Sri Ambati

Patrick Hall, Professor, AI Risk Management, The George Washington University H2O Open Source GenAI World SF 2023 Language models are incredible engineering breakthroughs but require auditing and risk management before productization. These systems raise concerns about toxicity, transparency and reproducibility, intellectual property licensing and ownership, disinformation and misinformation, supply chains, and more. How can your organization leverage these new tools without taking on undue or unknown risks? While language models and associated risk management are in their infancy, a small number of best practices in governance and risk are starting to emerge. If you have a language model use case in mind, want to understand your risks, and do something about them, this presentation is for you!

Risk Management for LLMs

Sri Ambati

Dr. Alexy Khrabrov, Open Source Science Community Director, IBM H2O Open Source GenAI World SF 2023 In this talk, Dr. Alexy Khrabrov, recently elected Chair of the new Generative AI Commons at Linux Foundation for AI & Data, outlines the OSS AI landscape, challenges, and opportunities. With new models and frameworks being unveiled weekly, one thing remains constant: community building and validation of all aspects of AI is key to reliable and responsible AI we can use for business and society needs. Industrial AI is one key area where such community validation can prove invaluable.

Open-Source AI: Community is the Way

Sri Ambati

Building Custom GenAI Apps at H2O

Sri Ambati

Megan Kurka, Vice President, Customer Data Scientist, H2O.ai H2O Open Source GenAI World SF 2023 Discover the transformative power of Applied Gen AI. Learn how the H2O team builds customized applications and workflows that integrate capabilities of Gen AI and AutoML specifically designed to address and enhance financial use cases. Explore real world examples, learn best practices, and witness firsthand how our innovative solutions are reshaping the landscape of finance technology.

Applied Gen AI for the Finance Vertical

Sri Ambati

Cutting Edge Tricks from LLM Papers

Sri Ambati

Pascal Pfeiffer, Principal Data Scientist, H2O.ai H2O Open Source GenAI World SF 2023 This talk dives into the expansive ecosystem of Large Language Models (LLMs), offering practitioners an insightful guide to various relevant applications, from natural language understanding to creative content generation. While exploring use cases across different industries, it also honestly addresses the current limitations of LLMs and anticipates future advancements.

Practitioner's Guide to LLMs: Exploring Use Cases and a Glimpse Beyond Curren...

Sri Ambati

Open Source h2oGPT with Retrieval Augmented Generation (RAG), Web Search, and...

Sri Ambati

KGM Mastering Classification and Regression with LLMs: Insights from Kaggle C...

Sri Ambati

LLM Interpretability

Sri Ambati

Never Reply to an Email Again

Sri Ambati

Introducción al Aprendizaje Automatico con H2O-3 (1)

Sri Ambati

Numerai is an open, crowd-sourced hedge fund powered by predictions from data scientists around the world. In return, participants are rewarded with weekly payouts in crypto. In this talk, Joe will give an overview of the Numerai tournament based on his own experience. He will then explain how he automates the time-consuming tasks such as testing different modelling strategies, scoring new datasets, submitting predictions to Numerai as well as monitoring model performance with H2O Driverless AI and R.

From Rapid Prototypes to an end-to-end Model Deployment: an AI Hedge Fund Use...

Sri Ambati

In this session, you will learn about what you should do after you’ve taken an AI transformation baseline. Over the span of this session, we will discuss the next steps in moving toward AI readiness through alignment of talent and tools to drive successful adoption and continuous use within an organization. To find additional videos on AI courses, earn badges, join the courses at H2O.ai Learning Center: https://training.h2o.ai/products/ai-foundations-course To find the Youtube video about this presentation: https://youtu.be/K1Cl3x3rd8g Speaker: Chemere Davis (H2O.ai - Senior Data Scientist Training Specialist)

AI Foundations Course Module 1 - Shifting to the Next Step in Your AI Transfo...

Sri Ambati

The chances of successfully implementing AI strategies within an organization significantly improve when you can recognize where your organization is on the maturity scale. Over this course, you will learn the keys to unlocking value with AI which include asking the right questions about the problems you are solving and ensuring you have the right cross-section of talent, tools, and resources. By the end of this module, you should be able to recognize where your organization is on the AI transformation spectrum and identify some strategies that can get you to the next stage in your journey. To find additional videos on AI courses, earn badges, join the courses at H2O.ai Learning Center: https://training.h2o.ai/products/ai-foundations-course To find the Youtube video about this presentation: https://youtu.be/PJgr2epM6qs Speakers: Chemere Davis (H2O.ai - Senior Data Scientist Training Specialist) Ingrid Burton (H2O.ai - CMO)

AI Foundations Course Module 1 - An AI Transformation Journey

Sri Ambati

Mehr von Sri Ambati (20)

H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day

Generative AI Masterclass - Model Risk Management.pptx

AI and the Future of Software Development: A Sneak Peek

LLMOps: Match report from the top of the 5th

Building, Evaluating, and Optimizing your RAG App for Production

Building LLM Solutions using Open Source and Closed Source Solutions in Coher...

Risk Management for LLMs

Open-Source AI: Community is the Way

Building Custom GenAI Apps at H2O

Applied Gen AI for the Finance Vertical

Cutting Edge Tricks from LLM Papers

Practitioner's Guide to LLMs: Exploring Use Cases and a Glimpse Beyond Curren...

Open Source h2oGPT with Retrieval Augmented Generation (RAG), Web Search, and...

KGM Mastering Classification and Regression with LLMs: Insights from Kaggle C...

LLM Interpretability

Never Reply to an Email Again

Introducción al Aprendizaje Automatico con H2O-3 (1)

From Rapid Prototypes to an end-to-end Model Deployment: an AI Hedge Fund Use...

AI Foundations Course Module 1 - Shifting to the Next Step in Your AI Transfo...

AI Foundations Course Module 1 - An AI Transformation Journey

Kürzlich hochgeladen

💥 You’re lucky! We’ve found two different (lead) developers that are willing to share their valuable lessons learned about using UiPath Document Understanding! Based on recent implementations in appealing use cases at Partou and SPIE. Don’t expect fancy videos or slide decks, but real and practical experiences that will help you with your own implementations. 📕 Topics that will be addressed: • Training the ML-model by humans: do or don't? • Rule-based versus AI extractors • Tips for finding use cases • How to start 👨‍🏫👨‍💻 Speakers: o Dion Morskieft, RPA Product Owner @Partou o Jack Klein-Schiphorst, Automation Developer @Tacstone Technology

DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam

UiPathCommunity

Strategies for Landing an Oracle DBA Job as a Fresher

Remote DBA Services

Effective data discovery is crucial for maintaining compliance and mitigating risks in today's rapidly evolving privacy landscape. However, traditional manual approaches often struggle to keep pace with the growing volume and complexity of data. Join us for an insightful webinar where industry leaders from TrustArc and Privya will share their expertise on leveraging AI-powered solutions to revolutionize data discovery. You'll learn how to: - Effortlessly maintain a comprehensive, up-to-date data inventory - Harness code scanning insights to gain complete visibility into data flows leveraging the advantages of code scanning over DB scanning - Simplify compliance by leveraging Privya's integration with TrustArc - Implement proven strategies to mitigate third-party risks Our panel of experts will discuss real-world case studies and share practical strategies for overcoming common data discovery challenges. They'll also explore the latest trends and innovations in AI-driven data management, and how these technologies can help organizations stay ahead of the curve in an ever-changing privacy landscape.

TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery

TrustArc

Sidekick Solutions uses Bonterra Impact Management (fka Social Solutions Apricot) and automation solutions to integrate data for business workflows. We believe integration and automation are essential to user experience and the promise of efficient work through technology. Automation is the critical ingredient to realizing that full vision. We develop integration products and services for Bonterra Case Management software to support the deployment of automations for a variety of use cases. This video focuses on the deployment of external web forms using Jotform for Bonterra Impact Management. This solution can be customized to your organization’s needs and deployed to support the common use cases below: - Intake and consent - Assessments - Surveys - Applications - Program registration Interested in deploying web form automations for Bonterra Impact Management? Contact us at sales@sidekicksolutionsllc.com to discuss next steps.

Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...

Jeffrey Haguewood

CNIC Information System with Pakdata Cf In Pakistan

danishmna97

MINDCTI Revenue Release Quarter One 2024

MIND CTI

Angeliki Cooney has spent over twenty years at the forefront of the life sciences industry, working out of Wynantskill, NY. She is highly regarded for her dedication to advancing the development and accessibility of innovative treatments for chronic diseases, rare disorders, and cancer. Her professional journey has centered on strategic consulting for biopharmaceutical companies, facilitating digital transformation, enhancing omnichannel engagement, and refining strategic commercial practices. Angeliki's innovative contributions include pioneering several software-as-a-service (SaaS) products for the life sciences sector, earning her three patents. As the Senior Vice President of Life Sciences at Avenga, Angeliki orchestrated the firm's strategic entry into the U.S. market. Avenga, a renowned digital engineering and consulting firm, partners with significant entities in the pharmaceutical and biotechnology fields. Her leadership was instrumental in expanding Avenga's client base and establishing its presence in the competitive U.S. market.

Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...

Angeliki Cooney

How to Troubleshoot Apps for the Modern Connected Worker

ThousandEyes

FWD Group - Insurer Innovation Award 2024

The Digital Insurer

Passkeys: Developing APIs to enable passwordless authentication Cody Salas, Sr Developer Advocate | Solutions Architect - Yubico Apidays New York 2024: The API Economy in the AI Era (April 30 & May 1, 2024) ------ Check out our conferences at https://www.apidays.global/ Do you want to sponsor or talk at one of our conferences? https://apidays.typeform.com/to/ILJeAaV8 Learn more on APIscene, the global media made by the community for the community: https://www.apiscene.io Explore the API ecosystem with the API Landscape: https://apilandscape.apiscene.io/

Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...

apidays

Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving

Edi Saputra

Tracing the root cause of a performance issue requires a lot of patience, experience, and focus. It’s so hard that we sometimes attempt to guess by trying out tentative fixes, but that usually results in frustration, messy code, and a considerable waste of time and money. This talk explains how to correctly zoom in on a performance bottleneck using three levels of profiling: distributed tracing, metrics, and method profiling. After we learn to read the JVM profiler output as a flame graph, we explore a series of bottlenecks typical for backend systems, like connection/thread pool starvation, invisible aspects, blocking code, hot CPU methods, lock contention, and Virtual Thread pinning, and we learn to trace them even if they occur in library code you are not familiar with. Attend this talk and prepare for the performance issues that will eventually hit any successful system. About authorWith two decades of experience, Victor is a Java Champion working as a trainer for top companies in Europe. Five thousands developers in 120 companies attended his workshops, so he gets to debate every week the challenges that various projects struggle with. In return, Victor summarizes key points from these workshops in conference talks and online meetups for the European Software Crafters, the world’s largest developer community around architecture, refactoring, and testing. Discover how Victor can help you on victorrentea.ro : company training catalog, consultancy and YouTube playlists.

Finding Java's Hidden Performance Traps @ DevoxxUK 2024

Victor Rentea

The Good, the Bad and the Governed - Why is governance a dirty word? David O'Neill, Chief Operating Officer - APIContext Apidays New York 2024: The API Economy in the AI Era (April 30 & May 1, 2024) ------ Check out our conferences at https://www.apidays.global/ Do you want to sponsor or talk at one of our conferences? https://apidays.typeform.com/to/ILJeAaV8 Learn more on APIscene, the global media made by the community for the community: https://www.apiscene.io Explore the API ecosystem with the API Landscape: https://apilandscape.apiscene.io/

Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...

apidays

Accelerating FinTech Innovation: Unleashing API Economy and GenAI Vasa Krishnan, Chief Technology Officer - FinResults Apidays New York 2024: The API Economy in the AI Era (April 30 & May 1, 2024) ------ Check out our conferences at https://www.apidays.global/ Do you want to sponsor or talk at one of our conferences? https://apidays.typeform.com/to/ILJeAaV8 Learn more on APIscene, the global media made by the community for the community: https://www.apiscene.io Explore the API ecosystem with the API Landscape: https://apilandscape.apiscene.io/

Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...

apidays

Architecting Cloud Native Applications

WSO2

In the thrilling conclusion to 2023, ransomware groups had a banner year, really outdoing themselves in the "make everyone's life miserable" department. LockBit 3.0 took gold in the hacking olympics, followed by the plucky upstarts Clop and ALPHV/BlackCat. Apparently, 48% of organizations were feeling left out and decided to get in on the cyber attack action. Business services won the "most likely to get digitally mugged" award, with education and retail nipping at their heels. Hackers expanded their repertoire beyond boring old encryption to the much more exciting world of extortion. The US, UK and Canada took top honors in the "countries most likely to pay up" category. Bitcoins were the currency of choice for discerning hackers, because who doesn't love untraceable money?

Ransomware_Q4_2023. The report. [EN].pdf

Overkill Security

2024: Domino Containers - The Next Step. News from the Domino Container commu...

Martijn de Jong

Boost Fertility New Invention Ups Success Rates.pdf

sudhanshuwaghmare1

Corporate and higher education. Two industries that, in the past, have had a clear divide with very little crossover. The difference in goals, learning styles and objectives paved the way for differing learning technologies platforms to evolve. Now, those stark lines are blurring as both sides are discovering they have content that’s relevant to the other. Join Tammy Rutherford as she walks through the pros and cons of corporate and higher ed collaborating. And the challenges of these different technology platforms working together for a brighter future.

Corporate and higher education May webinar.pptx

Rustici Software

Artificial Intelligence Chap.5 : Uncertainty

Khushali Kathiriya

Kürzlich hochgeladen (20)

DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam

Strategies for Landing an Oracle DBA Job as a Fresher

TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery

Web Form Automation for Bonterra Impact Management (fka Social Solutions Apri...

CNIC Information System with Pakdata Cf In Pakistan

MINDCTI Revenue Release Quarter One 2024

Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...

How to Troubleshoot Apps for the Modern Connected Worker

FWD Group - Insurer Innovation Award 2024

Apidays New York 2024 - Passkeys: Developing APIs to enable passwordless auth...

Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving

Finding Java's Hidden Performance Traps @ DevoxxUK 2024

Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...

Apidays New York 2024 - Accelerating FinTech Innovation by Vasa Krishnan, Fin...

Architecting Cloud Native Applications

Ransomware_Q4_2023. The report. [EN].pdf

2024: Domino Containers - The Next Step. News from the Domino Container commu...

Boost Fertility New Invention Ups Success Rates.pdf

Corporate and higher education May webinar.pptx

Artificial Intelligence Chap.5 : Uncertainty

Marc Stein, Underwrite.ai - Driverless AI Use Cases in Finance and Cancer Genomics - H2O World SF

1. Linear vs Nonlinear Credit Modeling Marc Stein Founder and CEO Underwrite.ai #H2OWORLD

2. Korean Credit Market • Highly efficient credit system • Very low default rate and commensurately low interest rates

3. This is a logistic regression model based upon four key attribute areas. How Credit Grade is Derived

4. Distribution of Credit Grades

5. Efficiency of Current Model Credit Grade AUC = 0.90640

6. Efficiency of Current Model This is a logistic regression model that works very well. It utilizes a small feature set very efficiently. This linear model is quite performant.

7. Nonlinear Approach But what if we take a nonlinear approach and use H20 and DAI to model the problem?

8. Nonlinear Approach Are there gains to be had by using 763 variables in a combinatorial manner in place of the linear model?

9. Nonlinear Approach Experiment: CDS3, 2018-12-19 00:04, 1.4.2 Settings: 8/5/5, seed=828672342, GPUs enabled Train data: CDS3_SELECTED Training.csv (60000, 67) Validation data: CDS3_Selected Validate.csv (30000, 67) Test data: CDS3_Selected Hold.csv (10000, 66) Target column: outcome (binary, 99.258% target class) System specs: Docker/Linux, 16 GB, 4 CPU cores, 1/1 GPU Max memory usage: 2.98 GB, 0.595 GB GPU Recipe: AutoDL (98 iterations, 8 individuals) Validation scheme: user-given validation data Feature engineering: 16749 features tested (210 selected) Timing: Data preparation: 8.89 secs Model and feature tuning: 640.33 secs (49 models trained) Feature evolution: 3085.32 secs (397 models trained) Final pipeline training: 148.83 secs (1 model trained) Validation score: AUC = 0.94953 +/- 0.0026775 (baseline) Validation score: AUC = 0.95162 +/- 0.0026263 (final pipeline) Test score: AUC = 0.95813 +/- 0.0072649 (final pipeline)

10. Efficiency of Current Model vs DAI Model Credit Grade AUC = 0.90640 DAI AUC = 0.95813

11. Take Away A highly efficient logistic regression model can be significantly outperformed by a GBM model which incorporates more data.

12. Less Efficient Models US Case Study Large consumer lender with an overall bad loan rate of 8.6%

13. US Case Study

14. Performance by Rate Tier

15. Performance by Rate Decile

16. Performance by FICO Decile

17. Performance by CVLink Decile

18. Performance by AI Decile

19. Combined Performance

20. Combined Performance

Marc Stein, Underwrite.ai - Driverless AI Use Cases in Finance and Cancer Genomics - H2O World SF

Empfohlen

Empfohlen

Weitere ähnliche Inhalte

Was ist angesagt?

Was ist angesagt? (20)

Ähnlich wie Marc Stein, Underwrite.ai - Driverless AI Use Cases in Finance and Cancer Genomics - H2O World SF

Ähnlich wie Marc Stein, Underwrite.ai - Driverless AI Use Cases in Finance and Cancer Genomics - H2O World SF (20)

Mehr von Sri Ambati

Mehr von Sri Ambati (20)

Kürzlich hochgeladen

Kürzlich hochgeladen (20)

Marc Stein, Underwrite.ai - Driverless AI Use Cases in Finance and Cancer Genomics - H2O World SF