Large Language Models (LLMs) have undergone continuous advancement, achieving significant breakthroughs in both inference speed and output quality, while increasingly gaining the capability to select and invoke external tools. A growing number of LLM-based agents have emerged--capable not only of engaging in multi-turn dialogues or solving International Mathematical Olympiad (IMO) level problems, but also of autonomously planning actions, making decisions, and interacting with external APIs, databases, and tools when faced with complex tasks. However, disparate databases, web services, and applications remain largely siloed, posing substantial engineering complexity for developers due to the lack of seamless integration and extensibility. To address this challenge, the Model Context Protocol (MCP) [1] has been introduced as a standardized interface for connecting LLMs with external data sources. MCP significantly reduces integration overhead and establishes a secure, trusted communication channel between MCP clients and servers, thereby fulfilling the scalability and interoperability requirements of AI-powered services.

This paper presents BARKPLUG V.2, a Large Language Model (LLM)-based chatbot system built using Retrieval Augmented Generation (RAG) pipelines to enhance the user experience and access to information within academic settings.The objective of BARKPLUG V.2 is to provide information to users about various campus resources, including academic departments, programs, campus facilities, and student resources at a university setting in an interactive fashion. Our system leverages university data as an external data corpus and ingests it into our RAG pipelines for domain-specific question-answering tasks. We evaluate the effectiveness of our system in generating accurate and pertinent responses for Mississippi State University, as a case study, using quantitative measures, employing frameworks such as Retrieval Augmented Generation Assessment(RAGAS). Furthermore, we evaluate the usability of this system via subjective satisfaction surveys using the System Usability Scale (SUS). Our system demonstrates impressive quantitative performance, with a mean RAGAS score of 0.96, and experience, as validated by usability assessments.

This paper proposes a novel framework for certifying the fairness of predictive models trained on biased data. It draws from query answering for incomplete and inconsistent databases to formulate the problem of consistent range approximation (CRA) of fairness queries for a predictive model on a target population. The framework employs background knowledge of the data collection process and biased data, working with or without limited statistics about the target population, to compute a range of answers for fairness queries. Using CRA, the framework builds predictive models that are certifiably fair on the target population, regardless of the availability of external data during training. The framework's efficacy is demonstrated through evaluations on real data, showing substantial improvement over existing state-of-the-art methods.

Data science has become increasingly essential for the production of official statistics, as it enables the automated collection, processing, and analysis of large amounts of data. With such data science practices in place, it enables more timely, more insightful and more flexible reporting. However, the quality and integrity of data-science-driven statistics rely on the accuracy and reliability of the data sources and the machine learning techniques that support them. In particular, changes in data sources are inevitable to occur and pose significant risks that are crucial to address in the context of machine learning for official statistics. This paper gives an overview of the main risks, liabilities, and uncertainties associated with changing data sources in the context of machine learning for official statistics. We provide a checklist of the most prevalent origins and causes of changing data sources; not only on a technical level but also regarding ownership, ethics, regulation, and public perception. Next, we highlight the repercussions of changing data sources on statistical reporting. These include technical effects such as concept drift, bias, availability, validity, accuracy and completeness, but also the neutrality and potential discontinuation of the statistical offering. We offer a few important precautionary measures, such as enhancing robustness in both data sourcing and statistical techniques, and thorough monitoring. In doing so, machine learning-based official statistics can maintain integrity, reliability, consistency, and relevance in policy-making, decision-making, and public discourse.

Data leakage is a sneaky issue that often plagues machine learning models. The term leakage refers to test data leaking into the training set. It happens when the model is trained on data that it shouldn't have access to during training, leading to overfitting and poor performance on unseen data. It's like training a student for a test using the test answers -- they'll do great on that specific test, but not so well on others. The goal of machine learning is to create models that can generalize and make accurate predictions on new, unseen data.

AI models will always be more accurate than gut feelings from scant data because they are objective and have "considered" a wide variety and volume of relevant data. Natural language processing allows data scientists to take newsfeeds, social media text, and publicly available business reports and convert them into data for decision making. By training AI models to learn patterns in all sorts of contextual data that pertain to a particular industry, supply chain managers are able to identify the events that will lead to disruption. They are also able to prescribe the best actions to take to avert disaster in their supply chain or pricing structures. Some AI/ML models can automate an appropriate response or alert the human in charge to make the necessary decisions to avert disruption.

Apache Kafka is a scalable and fault tolerant messaging system common in publish and subscribe (pub/sub) architectures. Apache Kafka is used for a range of use cases including message bus modernization, microservices architectures and ETL over streaming data. High throughput -- Each server is capable of handling 100s MB/sec of data. High availability -- Data can be stored redundantly in multiple servers and can survive individual server failure. High scalability -- New servers can be added over time to scale out the system.

Finding data for your analytics and machine learning initiatives has generally not been a problem for most organizations. Enterprise organizations collect data as an operational part of doing business. There are transactions, customer records, ERP, CRM, financials, human capital management, and more. Your organization has gathered metrics from web site visits and marketing email responses. There's plenty of data you already have that can fuel your data, analytics or machine learning initiatives.

The topic of insurtech is raising growing interest. This is mainly due to the immense size and importance of the insurance market, however, can also be attributed to the promising new opportunities offered by new technologies. The applications of these are very diverse and players in the insurtech space can be roughly divided into five categories. A unifying trait, however, is that many of these insurtechs have the common approach to tackling their problems by leveraging data and artificial intelligence (AI). Here, Mehrdad Piroozrom and Dr Babak Ahmadi discuss this for InsurTech Rising (read the original version here).

The topic of Insurtech is raising growing interest. This is mainly due to the immense size and importance of the insurance market, however, can also be attributed to the promising new opportunities offered by new technologies. As we pointed out in our last column "The Five Insurtech Battles", the applications are very diverse and players in the Insurtech space can be roughly divided into five categories. A unifying trait, however, is that many of these Insurtechs have the common approach to tackling their problems by leveraging data and Artificial Intelligence (AI), which we will discuss in more detail below. Insurance companies have always been very professional and efficient IT organizations compared to other industries and data has always played a major role.