Developing explainability methods for Natural Language Processing (NLP) models is a challenging task, for two main reasons. First, the high dimensionality of the data (large number of tokens) results in low coverage and in turn small contributions for the top tokens, compared to the overall model performance. Second, owing to their textual nature, the input variables, after appropriate transformations, are effectively binary (presence or absence of a token in an observation), making the input-output relationship difficult to understand. Common NLP interpretation techniques do not have flexibility in resolution, because they usually operate at word-level and provide fully local (message level) or fully global (over all messages) summaries. The goal of this paper is to create more flexible model explainability summaries by segments of observation or clusters of words that are semantically related to each other. In addition, we introduce a root cause analysis method for NLP models, by analyzing representative False Positive and False Negative examples from different segments. At the end, we illustrate, using a Yelp review data set with three segments (Restaurant, Hotel, and Beauty), that exploiting group/cluster structures in words and/or messages can aid in the interpretation of decisions made by NLP models and can be utilized to assess the model's sensitivity or bias towards gender, syntax, and word meanings.

Deep Learning (DL) advances have cleared the way for intriguing new applications and are influencing the future of Artificial Intelligence (AI) technology. However, a typical concern for DL models is their explainability, as experts commonly agree that Neural Networks (NNs) function as black boxes. We do not precisely know what happens inside, but we know that the given input is somehow processed, and as a result, we obtain something as output. For this reason, DL models can often be difficult to understand or interpret. Understanding why a model makes certain predictions or how to improve it can be challenging.

Evaluating model relevance does not stop at measuring its performance. For many reasons it is important to know how it ended up making such predictions. A machine learning model can be explained using local explainability or global explainability. In this article, we will use a complementary approach by combining explainability and sample picking. Sample picking is a process with great added value to better understand models, their strengths and weaknesses.

This article is part of a series where we walk step by step in solving fintech problems with Machine Learning using "All lending club loan data". In previous articles, we prepared a dataset and built a Logistic Regression model, and we discussed the most common "ML model evaluation metrics" for a classification problem in the fintech space. This article will try to "understand" how our model decision works and what packages can help us to answer this question. Machine learning models are frequently named "black boxes". They produce highly accurate predictions.

As complex machine learning models are increasingly used in sensitive applications like banking, trading or credit scoring, there is a growing demand for reliable explanation mechanisms. Local feature attribution methods have become a popular technique for post-hoc and model-agnostic explanations. However, attribution methods typically assume a stationary environment in which the predictive model has been trained and remains stable. As a result, it is often unclear how local attributions behave in realistic, constantly evolving settings such as streaming and online applications. In this paper, we discuss the impact of temporal change on local feature attributions. In particular, we show that local attributions can become obsolete each time the predictive model is updated or concept drift alters the data generating distribution. Consequently, local feature attributions in data streams provide high explanatory power only when combined with a mechanism that allows us to detect and respond to local changes over time. To this end, we present CDLEEDS, a flexible and model-agnostic framework for detecting local change and concept drift. CDLEEDS serves as an intuitive extension of attribution-based explanation techniques to identify outdated local attributions and enable more targeted recalculations. In experiments, we also show that the proposed framework can reliably detect both local and global concept drift. Accordingly, our work contributes to a more meaningful and robust explainability in online machine learning.

Health care professionals rely on treatment search engines to efficiently find adequate clinical trials and early access programs for their patients. However, doctors lose trust in the system if its underlying processes are unclear and unexplained. In this paper, a model-agnostic explainable method is developed to provide users with further information regarding the reasons why a clinical trial is retrieved in response to a query. To accomplish this, the engine generates features from clinical trials using by using a knowledge graph, clinical trial data and additional medical resources. and a crowd-sourcing methodology is used to determine their importance. Grounded on the proposed methodology, the rationale behind retrieving the clinical trials is explained in layman's terms so that healthcare processionals can effortlessly perceive them. In addition, we compute an explainability score for each of the retrieved items, according to which the items can be ranked. The experiments validated by medical professionals suggest that the proposed methodology induces trust in targeted as well as in non-targeted users, and provide them with reliable explanations and ranking of retrieved items.

Establishing an expectation for trust around AI technologies may soon become one of the most important skills provided by Data Scientists. Significant research investments are underway in this area, and new tools are being developed, such as Shapash, an open-source Python library that helps Data Scientists make machine learning models…

Going from left to right, we consider increasingly complex functions. These neighborhoods, in other words, need to become more and more disjoint as the function becomes more complex. Indeed, we quantify "disjointedness" of the neighborhoods via a term denoted by and relate it to the complexity of the function class, and subsequently, its generalization properties. There has been a growing interest in interpretable machine learning (IML), towards helping users better understand how their ML models behave. IML has become a particularly relevant concern especially as practitioners aim to apply ML in important domains such as healthcare [Caruana et al., '15], financial services [Chen et al., '18], and scientific discovery [Karpatne et al., '17]. While much of the work in IML has been qualitative and empirical, in our recent ICLR21 paper, we study how concepts in interpretability can be formally related to learning theory.

The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpretable by humans, and how can this be assessed? We focus on two definitions of interpretability that have been introduced in the machine learning literature: simulatability (a user's ability to run a model on a given input) and "what if" local explainability (a user's ability to correctly indicate the outcome to a model under local changes to the input). Through a user study with 1000 participants, we test whether humans perform well on tasks that mimic the definitions of simulatability and "what if" local explainability on models that are typically considered locally interpretable. We find evidence consistent with the common intuition that decision trees and logistic regression models are interpretable and are more interpretable than neural networks. We propose a metric - the runtime operation count on the simulatability task - to indicate the relative interpretability of models and show that as the number of operations increases the users' accuracy on the local interpretability tasks decreases.