O'Reilly on Data

DECEMBER 12, 2019

Model debugging is an emergent discipline focused on finding and fixing problems in ML systems. In addition to newer innovations, the practice borrows from model risk management, traditional model diagnostics, and software testing. Figure 1 illustrates an example adversarial search for an example credit default ML model.

Machine Learning 191

Machine Learning Modeling Testing Risk Management 191

Domino Data Lab

OCTOBER 7, 2020

MANOVA, for example, can test if the heights and weights in boys and girls is different. This statistical test is correct because the data are (presumably) bivariate normal. In high dimensions the data assumptions needed for statistical testing are not met. The accuracy of any predictive model approaches 100%.

Statistics 145

Statistics Testing Predictive Modeling Modeling 145

Domino Data Lab

JULY 28, 2021

There are many software packages that allow anyone to build a predictive model, but without expertise in math and statistics, a practitioner runs the risk of creating a faulty, unethical, and even possibly illegal data science application. All models are not made equal. After cleaning, the data is now ready for processing.

Data Science 110

Data Science Statistics Recreation/Entertainment Predictive Analytics 110

Cloudera

FEBRUARY 16, 2022

They define each stage from data ingest, feature engineering, model building, testing, deployment and validation. Figure 04: Applied Machine Learning Prototypes (AMPs). Given the complexity of some ML models, especially those based on Deep Learning (DL) Convolutional Neural Networks (CNNs), there are limits to interpretability.

Machine Learning 81

Machine Learning Modeling Metadata Recreation/Entertainment 81

IBM Big Data Hub

OCTOBER 16, 2023

Machine learning in financial transactions ML and deep learning are widely used in banking, for example, in fraud detection. Banks and other financial institutions train ML models to recognize suspicious online transactions and other atypical transactions that require further investigation.

Machine Learning 51

Machine Learning Marketing Forecasting Modeling 51

IBM Big Data Hub

FEBRUARY 14, 2024

AI platforms can use machine learning and deep learning to spot suspicious or anomalous transactions. Banks and other lenders can use ML classification algorithms and predictive models to suggest loan decisions.

Cost-Benefit 88

Cost-Benefit Insurance Unstructured Data Machine Learning 88

Smarten

APRIL 19, 2024

Assisted Predictive Modeling and Auto Insights to create predictive models using self-guiding UI wizard and auto-recommendations The Future of AI in Analytics The C=suite executive survey revealed that 93% felt that data strategy is critical to getting value from generative AI, but a full 57% had made no changes to their data.

Analytics 57

Analytics Predictive Modeling KPI Machine Learning 57

Domino Data Lab

AUGUST 22, 2019

Many thanks to Addison-Wesley Professional for providing the permissions to excerpt “Natural Language Processing” from the book, Deep Learning Illustrated by Krohn , Beyleveld , and Bassens. The excerpt covers how to create word vectors and utilize them as an input into a deep learning model.

Deep Learning 111

Deep Learning Modeling Metrics Testing 111

Alation

APRIL 14, 2022

Automatic sampling to test transformation. They strove to ramp up skills in all manner of predictive modeling, machine learning, AI, or even deep learning. AI/ML models pose a problem with versioning results and testing using unique testing and algorithms. Visual Profiling. Scheduling.

Metadata 59

Metadata Data Governance Modeling Data-driven 59

CIO Business Intelligence

MARCH 22, 2023

The new class often uses advanced techniques such as deep learning, natural language processing, and computer vision to analyze and extract insights from the data. Additionally, federated learning does not address the inference stage, which still exposes data to the ML model during cloud or edge device deployment.

Machine Learning 105

Machine Learning Cost-Benefit Modeling Risk 105

Domino Data Lab

APRIL 21, 2021

deep learning) there is no guaranteed explainability. We will go through a typical ML pipeline, where we do data ingestion, exploratory data analysis, feature engineering, model training and evaluation. This is to prevent any information leakage into our test set. 2f%% of the test set." 2f%% of the test set."

Statistics 69

Statistics Machine Learning Modeling Metrics 69

DataRobot Blog

DECEMBER 15, 2022

While AI-powered forecasting can help retailers implement sales and demand forecasting—this process is very complex, and even highly data-driven companies face key challenges: Scale: Thousands of item combinations make it difficult to manually build predictive models.

Forecasting 81

Forecasting Modeling ROI Machine Learning 81

Domino Data Lab

JULY 9, 2019

Diving into examples of building and deploying ML models at The New York Times including the descriptive topic modeling-oriented Readerscope (audience insights engine), a prediction model regarding who was likely to subscribe/cancel their subscription, as well as prescriptive example via recommendations of highly curated editorial content.

Data Science 112

Data Science Machine Learning Advertising Modeling 112

Domino Data Lab

AUGUST 1, 2021

The interest in interpretation of machine learning has been rapidly accelerating in the last decade. This can be attributed to the popularity that machine learning algorithms, and more specifically deep learning, has been gaining in various domains. Methods for explaining Deep Learning. show_in_notebook().

Modeling 139

Modeling Deep Learning Machine Learning Knowledge Discovery 139

O'Reilly on Data

MARCH 24, 2020

For example, a pre-existing correlation pulled from an organization’s database should be tested in a new experiment and not assumed to imply causation [3] , instead of this commonly encountered pattern in tech: A large fraction of users that do X do Z. In particular, determining causation from correlation can be difficult.

Machine Learning 346

Machine Learning Statistics Data Quality Modeling 346