Blogs about

Data Science

The Holistic AI Library's New Explainability Module: Demystifying black-box models
Data Science
Data Science
The Holistic AI Library's New Explainability Module: Demystifying black-box models
Holistic AI are proud to present our new explainability module, the latest addition to the open-source Holistic AI Library. This development marks another significant step in our ongoing mission to enhance the transparency and security of machine learning models.
Measuring Effectiveness in Machine Learning Classification Models
Data Science
Data Science
Measuring Effectiveness in Machine Learning Classification Models
Bias in machine learning (ML) refers to unfair discrimination in the outcomes produced by an algorithm for certain disadvantaged groups. Most of the time, this problem comes from the data used to train these algorithms, producing models that inadvertently encode pre-existing societal biases and prejudices.
Visualising Bias Metrics: Insights from Holistic AI's Open-Source Library
Data Science
Data Science
Visualising Bias Metrics: Insights from Holistic AI's Open-Source Library
Visualising information is an integral part of the decision-making process. When we visualise a dataset, our aim is to make the information clear and objective, facilitating a more sophisticated understanding and adding value to the information.
Machine Learning Classification Models: Exploring the Fairness-Accuracy Trade-Off
Machine Learning Classification Models: Exploring the Fairness-Accuracy Trade-Off
In this blog, we will explore the fairness-accuracy trade-off analysis for classification models, examining its significance with a pertinent case study.
Explaining Machine Learning Outputs: The Role of Feature Importance
Data Science
Data Science
Explaining Machine Learning Outputs: The Role of Feature Importance
In an age where artificial intelligence permeates nearly every aspect of our lives, the inner workings of these intelligent systems often remain shrouded in mystery. However, with the rise of explainable AI (XAI), a groundbreaking paradigm is transforming the AI landscape, bringing transparency and understanding to complex machine learning models.
Fact or Fiction: What Are the Different LLM Hallucination Types?
Data Science
Data Science
Fact or Fiction: What Are the Different LLM Hallucination Types?
‍Large language models (LLMs) have, perhaps more than anything else within the field of artificial intelligence, embedded AI in the public psyche, opening people’s eyes to both its risks and rewards.
Debiasing Artificial Neural Networks with Holistic AI and PyTorch
Data Science
Data Science
Debiasing Artificial Neural Networks with Holistic AI and PyTorch
The blog post discusses how to mitigate bias in artificial neural networks using the Holistic AI and PyTorch libraries. The Holistic AI Library is an open-source resource that provides tools for analyzing and visualizing bias in machine learning models. PyTorch is a popular machine-learning library that provides tools for building and training neural network models.
How to Create Interactive Visualisations in Colab with Holistic AI and Plotly
Data Science
Data Science
How to Create Interactive Visualisations in Colab with Holistic AI and Plotly
Visualizing data is essential for analysis, enabling pattern recognition and informed decision-making. In machine learning, it helps eliminate biases. Use Holistic AI, sklearn, and Plotly to build interactive bias plots in Python without local installations, enhancing AI system trustworthiness.
Build Your Own Bias Measuring and Mitigation Dashboard in 5 Steps
Data Science
Data Science
Build Your Own Bias Measuring and Mitigation Dashboard in 5 Steps
AI is becoming increasingly woven into the fabric of our everyday lives. It is, therefore, imperative that we address the potential harms associated with bias in AI systems – that means eliminating algorithms that perpetuate discrimination, reinforce inequality and yield unfair outcomes.
Using Python to Mitigate Bias and Discrimination in Machine Learning Models
Data Science
Data Science
Using Python to Mitigate Bias and Discrimination in Machine Learning Models
Machine learning models can be used in critical applications, such as hiring processes, the judicial system, credit scoring, or facial recognition systems. In these cases, it is essential to ensure that the algorithms used do not discriminate against those they are assessing.There have been a number of high-profile, real-world instances of AI systems displaying bias and materially impacting particular groups. A 2018 study, for example, found that three popular facial recognition systems appeared to be biased, and incorrectly classified up to 34.7% of Black women compared to a 0.8% error rate for white men.
Bias Mitigation Strategies and Techniques for Classification Tasks
Data Science
Data Science
Bias Mitigation Strategies and Techniques for Classification Tasks
To mitigate the bias phenomenon in machine learning models, different methods or techniques have been developed. This post aims to present some of the strategies available in the literature that approach this problem in classification tasks.
Holistic AI Library Tutorial: Bias Measuring and Mitigation in Regression Tasks
Data Science
Data Science
Holistic AI Library Tutorial: Bias Measuring and Mitigation in Regression Tasks
Bias phenomenon can occur in different tasks for machine learning models, regression is one of them, where predictions deviate for specific subgroups in the dataset. Once the bias is detected, we can use different techniques to mitigate it from the model, to do that, the "holisticai" library is an exciting tool that helps us to do it.
Holistic AI Library Tutorial: Fairness Analysis for Binary Classification with Python
Holistic AI Library Tutorial: Fairness Analysis for Binary Classification with Python
Machine learning models have become a part of our day-to-day life, increasingly being used to make predictions and decisions, classify images or text, recognise objects, and recommend products, for example. These tools have a number of limitations and challenges of these models, especially in relation to bias. In this blog post, we use the COMPAS tool as an example of a biased system and illustrate how bias can be measured using Holistic AI’s open-source library.
How Do You Measure Algorithm Efficacy?
How Do You Measure Algorithm Efficacy?
Measuring algorithm efficacy gives important insights into how well the model is working and does what it is designed to do. In this blog post, we give an overview of some different metrics that can be used to measure the performance of classification and regression systems.
Measuring and Mitigating Bias: Introducing Holistic AI's Open-Source Library
Data Science
Data Science
Measuring and Mitigating Bias: Introducing Holistic AI's Open-Source Library
Today, artificial intelligence (AI) is increasingly present in our lives and becoming a fundamental part of many systems and applications. However, like any technology, it is important to ensure that AI-based solutions are trustworthy and fair. That's where the Holistic AI library comes in. In this blog post, we provide an overview of Holistic AI’s Bias analysis and mitigation framework, defining bias and how it can be mitigated before giving an overview of the bias metrics and mitigations available in the Holistic AI library.
SHAP Values: An Intersection Between Game Theory and Artificial Intelligence
SHAP Values: An Intersection Between Game Theory and Artificial Intelligence
Game Theory was an intellectual advance built at final of World War II and initially had mathematicians as its main contributors. Over time, researchers from other areas began to adopt this theoretical framework, highlighting economists and political scientists. The Shapley value describes a method to distribute the total gain to players if they all collaborate in a specific coalition strategy. We can describe that SHAP (SHapley Additive exPlanation) values attribute to each feature the change in the expected model prediction when conditioning on that feature.
Disparate Impact in Bias Audits: Evaluating the DCWP’s Impact Ratio Metrics for Regression Systems
Disparate Impact in Bias Audits: Evaluating the DCWP’s Impact Ratio Metrics for Regression Systems
In recent years, the fairness of automated employment decision tools (AEDTs) has received increasing attention. In November 2021, the New York City Council passed Local Law 144, which mandates bias audits of these systems.
Overcoming Small Sample Sizes When Identifying Bias
Overcoming Small Sample Sizes When Identifying Bias
Under Local Law 144, employers and employment agencies are required to commission independent, impartial bias audits of their tools, where, under the latest version of the Department of Consumer and Worker Protection’s (DCWP) proposed rules, bias should be determined using impact ratios based on outcomes for different subgroups. In this blog post, we outline the metrics required to conduct the bias audit, how small sample sizes can pose issues, and how they can be dealt with when carrying out audits.
Back to Our Blogs

Manage risks. Embrace AI.

Our AI Governance, Risk and Compliance platform empowers your enterprise to confidently embrace AI

Get Started
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Solutions
NYC Bias AuditEU AI Act ReadinessDigital Services Act AuditAI Risk ManagementEEOC Bias Audit
Resources
BlogNewsPapersEventsOpen Source
Company
AboutPress
Careers
We're hiring!
Case Studies

© 2023 Holistic AI. All rights reserved.

Privacy PolicyTerms & Conditions

DISCLAIMER: The information provided on this website does not, and is not intended to, constitute legal advice; instead, all information, content, and materials available on this site are for general informational purposes only. Information on this website may not constitute the most up-to-date legal or other information. This website contains links to other third-party websites. Such links are only for the convenience of the reader, user or browser; Holistic AI does not recommend or endorse the contents of third-party sites.

Readers of this website should contact their attorney to obtain advice with respect to any particular legal matter. No reader, user, or browser of this site should act or refrain from acting on the basis of information on this site without first seeking legal advice from counsel in the relevant jurisdiction. Only your individual attorney can provide assurances that the information contained herein – and your interpretation of it – is applicable or appropriate to your particular situation. Use of, and access to, this website or any of the links or resources contained within the site do not create an attorney-client relationship between the reader, user, or browser and website authors, contributors, contributing law firms, or committee members and their respective employers.

The views expressed at, or through, this site are those of the individual authors writing in their individual capacities only – not those of their respective employers, Holistic AI, or committee/task force as a whole. All liability with respect to actions taken or not taken based on the contents of this site are hereby expressly disclaimed. The content on this posting is provided "as is;" no representations are made that the content is error-free.