Conversational recommender systems (CRS) enable users to articulate their preferences and provide feedback through natural language. With the advent of large language models (LLMs), the potential to enhance user engagement with CRS and augment the recommendation process with LLM-generated content has received increasing attention. However, the efficacy of LLM-powered CRS is contingent upon the use of prompts, and the subjective perception of recommendation quality can differ across various recommendation domains. Therefore, we have developed a ChatGPT-based CRS to investigate the impact of these two factors, prompt guidance (PG) and recommendation domain (RD), on the overall user experience of the system. We conducted an online empirical study (N = 100) by employing a mixed-method approach that utilized a between-subjects design for the variable of PG (with vs. without) and a within-subjects design for RD (book recommendations vs. job recommendations). The findings reveal that PG can substantially enhance the system's explainability, adaptability, perceived ease of use, and transparency. Moreover, users are inclined to perceive a greater sense of novelty and demonstrate a higher propensity to engage with and try recommended items in the context of book recommendations as opposed to job recommendations. Furthermore, the influence of PG on certain user experience metrics and interactive behaviors appears to be modulated by the recommendation domain, as evidenced by the interaction effects between the two examined factors. This work contributes to the user-centered evaluation of ChatGPT-based CRS by investigating two prominent factors and offers practical design guidance.

We analyze the expected behavior of an advanced artificial agent with a learned goal planning in an unknown environment. Given a few assumptions, we argue that it will encounter a fundamental ambiguity in the data about its goal. For example, if we provide a large reward to indicate that something about the world is satisfactory to us, it may hypothesize that what satisfied us was the sending of the reward itself; no observation can refute that. Then we argue that this ambiguity will lead it to intervene in whatever protocol we set up to provide data for the agent about its goal. We discuss an analogous failure mode of approximate solutions to assistance games. Finally, we briefly review some recent approaches that may avoid this problem.

Collaborative filtering algorithms have the advantage of not requiring sensitive user or item information to provide recommendations. However, they still suffer from fairness related issues, like popularity bias. In this work, we argue that popularity bias often leads to other biases that are not obvious when additional user or item information is not provided to the researcher. We examine our hypothesis in the book recommendation case on a commonly used dataset with book ratings. We enrich it with author information using publicly available external sources. We find that popular books are mainly written by US citizens in the dataset, and that these books tend to be recommended disproportionally by popular collaborative filtering algorithms compared to the users' profiles. We conclude that the societal implications of popularity bias should be further examined by the scholar community.

"Good friends, good books, and a sleepy conscience: this is the ideal life." I hope you're reading this blog in your pyjamas looking forward to a rejuvenating and healthy weekend. So, I have been working on multiple projects from creating MLE/MLOps courses to developing end-to-end ML systems at scale and I have realized that oftentimes, I am either revisiting a book that I've read or I'm referring to a book that I just skimmed through but never got the chance to really read it. This week, I want to share with you the books that I personally feel every ML Enthusiast and Practitioner should read to get a sense of the breadth(ideas) and depth(grok) of this field respectively. It is a short and crisp list covering a majority of ML topics.

This is an original work submission presented for completion of Udacity's Data Scientist Nanodegree capstone project. This blog shows how to build a Book Recommendation Engine using machine learning techniques, Python and its libraries. The code is structured so it can later be deployed as a web app. The goal of this project is to develop a Book Recommendation engine based on information entered by the user. The project uses a dataset containing six million ratings for the ten thousand most popular books and classified with tags.

Bill Gates, captured on April 19, 2018 in Berlin, Germany. Tech titans have a long history of making book recommendations. In 2015, Mark Zuckerberg launched a book club via Facebook, noting a must-read every two weeks. The year opened with Moisés Naím's The End of Power: From Boardrooms to Battlefields and Churches to States, Why Being In Charge Isn't What It Used to Be and closed out with David Deutsch's The Beginning of Infinity: Explanations that Transform the World; in between were titles on racism, genetics, religion, medicine, and sociology, and a smattering of science fiction novels. Jeff Bezos, owner of "bookstore killer" Amazon, had a book list on the platform in 2013 that included a variety of entrepreneur-focused books, like the iconic The Innovators Dilemma by Clayton Christensen and Built to Last: Successful Habits of Visionary Companies by Jim Collins.

Artificial intelligence is not only poised to disrupt industries and workplaces, but also the way that we as humans interact. As our AI journey continues, we will increasingly see the advancements that it provides play out in our daily lives. Technologists like myself are not the only ones thinking about our AI future and the implications for society; a variety of authors have explored the topic. For those fascinated with AI or looking to enter the field, reading about the evolution of technology and its potential is a good place to start. As a scientist, avid reader and follower of AI technology, here are a few of my top book recommendations around this fascinating topic.

Click to learn more about author Alejandro Correa Bahnsen. There are a variety of Machine Learning algorithms, and each has its own strengths and weaknesses. In this second article in a series on Machine Learning algorithms, I introduce Random Forests, a supervised algorithm used for classification and regression. If you missed my Introduction to Machine Learning and Decision Trees, I encourage you to read that article first, as it provides a foundation that I'm building on. Before we dig into Random Forests, you must first understand the concept of an ensemble-learning model.

We created a list of artificial intelligence and machine learning experts from different companies, startups, and universities -- and scanned their Twitter profiles for book recommendations. Did you discover new books to read? Hold down the below so other people will read it too.

Publishers have always emphasized the power of word-of-mouth marketing when it comes to selling books. Booksellers are expected to hand-sell titles to bookstore patrons for this reason, and the shelves are often peppered with "employee recommendation" markers meant to boost interest in specific books. So it should come as no surprise that this process is increasingly becoming automated. There have been multiple news reports of publishers getting creative with their recommendation processes over the past few years: In 2014, Penguin created the "Penguin Hotline" for the holidays in which interested customers submitted an online dossier on their gift recipients and soon after received recommendations directly from one of the publisher's employees. Last year, NPR created an online "Book Concierge" that aggregated the titles reviewed by the organization over the course of the year and applied a set of useful filters.