In this work, we propose a simple and computationally efficient framework for evaluating whether machine learning models align with the structure of the data they learn from; that is, whether the model says what the data says. Unlike existing interpretability methods that focus exclusively on explaining model behavior, our approach establishes a baseline derived directly from the data itself. Drawing inspiration from Rubin's Potential Outcomes Framework, we quantify how strongly each feature separates the two outcome groups in a binary classification task, moving beyond traditional descriptive statistics to estimate each feature's effect on the outcome. By comparing these data-derived feature rankings with model-based explanations, we provide practitioners with an interpretable and model-agnostic method for assessing model-data alignment.

The phenomenon of "black swans" has posed a fundamental challenge to performance of classical machine learning models. The perceived rise in frequency of outlier conditions, especially in post-pandemic environment, has necessitated exploration of synthetic data as a complement to real data in model training. This article provides a general overview and experimental investigation of the zGAN model architecture developed for the purpose of generating synthetic tabular data with outlier characteristics. The model is put to test in binary classification environments and shows promising results on realistic synthetic data generation, as well as uplift capabilities vis-\`a-vis model performance. A distinctive feature of zGAN is its enhanced correlation capability between features in the generated data, replicating correlations of features in real training data. Furthermore, crucial is the ability of zGAN to generate outliers based on covariance of real data or synthetically generated covariances. This approach to outlier generation enables modeling of complex economic events and augmentation of outliers for tasks such as training predictive models and detecting, processing or removing outliers. Experiments and comparative analyses as part of this study were conducted on both private (credit risk in financial services) and public datasets.

Large Language Models(LLMs) have been attracting attention due to a ability called in-context learning(ICL). ICL, without updating the parameters of a LLM, it is possible to achieve highly accurate inference based on rules ``in the context'' by merely inputting a training data into the prompt. Although ICL is a developing field with many unanswered questions, LLMs themselves serves as a inference model, seemingly realizing inference without explicitly indicate ``inductive bias''. On the other hand, a code generation is also a highlighted application of LLMs. The accuracy of code generation has dramatically improved, enabling even non-engineers to generate code to perform the desired tasks by crafting appropriate prompts. In this paper, we propose a novel ``learning'' method called an ``Inductive-Bias Learning (IBL)'', which combines the techniques of ICL and code generation. An idea of IBL is straightforward. Like ICL, IBL inputs a training data into the prompt and outputs a code with a necessary structure for inference (we referred to as ``Code Model'') from a ``contextual understanding''. Despite being a seemingly simple approach, IBL encompasses both a ``property of inference without explicit inductive bias'' inherent in ICL and a ``readability and explainability'' of the code generation. Surprisingly, generated Code Models have been found to achieve predictive accuracy comparable to, and in some cases surpassing, ICL and representative machine learning models. Our IBL code is open source: https://github.com/fuyu-quant/IBLM

As a Harry Potter fan and a programmer, I can't help but be reminded of the wizarding world when I think about coding. Just like a young wizard learning spells and incantations, we programmers spend hours upon hours learning syntax and debugging code. But what if we had a way to get a little help with the heavy lifting? What if we could wave a wand and it could effortlessly write code for us!! Seems like it might be actually achievable. In this post, we will allow ChatGPT to do the magic and help us lend a hand in writing code.

This article was published as a part of the Data Science Blogathon. The Titanic ship disaster is one of the most infamous shipwrecks. The luxury cruiser, touted to be one of the safest when launched, sank thousands of passengers due to an accident with an iceberg. Out of 2224 passengers, 1502 passengers died due to the shipwreck. The accident had made some researchers wonder what could have led to the survival of some and the demise of others.

Null values are a big problem in machine learning and deep learning. If you are using sklearn, TensorFlow, or any other machine learning or deep learning packages, it is required to clean up null values before you pass your data to the machine learning or deep learning framework. Otherwise, it will give you a long and ugly error message. In this article, we will work on how to handle null values. First, there will be some very simple methods and slowly we will move toward some more complex and more efficient ways.

You've probably heard of Kaggle data science competitions, but did you know that Kaggle has many other features that can help you with your next machine learning project? For people looking for datasets for their next machine learning project, Kaggle allows you to access public datasets by others and share your own datasets. For those looking to build and train their own machine learning models, Kaggle also offers an in-browser notebook environment and some free GPU hours. You can also look at other people's public notebooks as well! Other than the website, Kaggle also has a command-line interface (CLI) which you can use within the command line to access and download datasets.

I am preparing my very first Kaggle submission, which will be for the Titanic competition, and was wondering what a respectable or even good score would be? This course is designed to teach the student advanced classification techniques that will enable him to enter Kaggle's Titanic competition and achieve an improved score by using standard machine learning methods. After the student is introduced to the course, he will receive an introduction to Python's machine learning library, sklearn. The student will also be introduced to the website, OpenML, which is a repository of a multitude of datasets. The Titanic dataset in the OpenML website is used in the lessons in this course all the way up to the point that the student is invited to enter the Kaggle Titanic competition and employ all of the advanced classification techniques that he has learned in the course.

We will cover categorical and ordinal features. In particular, what kind of pre-processing will be used for each model type? What is the difference between categorical and ordinal features and how we can generate new features from them? First, let's look at several rows from the Titanic dataset and find categorical features here. Their names are Sex, Cabin, and Embarked.

AutoML is an interesting field in the Machine Learning industry promising faster model generation cycles. In recent time I have been working on a Deep Learning project with Tensroflow and Keras. Out of sheer curiosity and the purpose of always learning, I decided to try out Automated Deep Learning more specifically AutoKeras. The motivation behind this article is due to the small number of resources on the topic. Starting out I searched only for information where I found a very small number of walkthroughs and none of which are up to date. With that said, the scope of this article is a basic use case of AutoKeras and a file structure layout .. ofc GitHub repo included:D.