Personal Assistant Systems
ROLeR: Effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems
Zhang, Yi, Qiu, Ruihong, Liu, Jiajun, Wang, Sen
Offline reinforcement learning (RL) is an effective tool for real-world recommender systems with its capacity to model the dynamic interest of users and its interactive nature. Most existing offline RL recommender systems focus on model-based RL through learning a world model from offline data and building the recommendation policy by interacting with this model. Although these methods have made progress in the recommendation performance, the effectiveness of model-based offline RL methods is often constrained by the accuracy of the estimation of the reward model and the model uncertainties, primarily due to the extreme discrepancy between offline logged data and real-world data in user interactions with online platforms. To fill this gap, a more accurate reward model and uncertainty estimation are needed for the model-based RL methods. In this paper, a novel model-based Reward Shaping in Offline Reinforcement Learning for Recommender Systems, ROLeR, is proposed for reward and uncertainty estimation in recommendation systems. Specifically, a non-parametric reward shaping method is designed to refine the reward model. In addition, a flexible and more representative uncertainty penalty is designed to fit the needs of recommendation systems. Extensive experiments conducted on four benchmark datasets showcase that ROLeR achieves state-of-the-art performance compared with existing baselines. The source code can be downloaded at https://github.com/ArronDZhang/ROLeR.
A Comprehensive Review of Recommender Systems: Transitioning from Theory to Practice
Raza, Shaina, Rahman, Mizanur, Kamawal, Safiullah, Toroghi, Armin, Raval, Ananya, Navah, Farshad, Kazemeini, Amirmohammad
Recommender Systems (RS) play an integral role in enhancing user experiences by providing personalized item suggestions. This survey reviews the progress in RS inclusively from 2017 to 2024, effectively connecting theoretical advances with practical applications. We explore the development from traditional RS techniques like content-based and collaborative filtering to advanced methods involving deep learning, graph-based models, reinforcement learning, and large language models. We also discuss specialized systems such as context-aware, review-based, and fairness-aware RS. The primary goal of this survey is to bridge theory with practice. It addresses challenges across various sectors, including e-commerce, healthcare, and finance, emphasizing the need for scalable, real-time, and trustworthy solutions. Through this survey, we promote stronger partnerships between academic research and industry practices. The insights offered by this survey aim to guide industry professionals in optimizing RS deployment and to inspire future research directions, especially in addressing emerging technological and societal trends
Evaluating the performance-deviation of itemKNN in RecBole and LensKit
Schmidt, Michael, Nitschke, Jannik, Prinz, Tim
This study examines the performance of item-based k-Nearest Neighbors (ItemKNN) algorithms in the RecBole and LensKit recommender system libraries. Using four data sets (Anime, Modcloth, ML-100K, and ML-1M), we assess each library's efficiency, accuracy, and scalability, focusing primarily on normalized discounted cumulative gain (nDCG). Our results show that RecBole outperforms LensKit on two of three metrics on the ML-100K data set: it achieved an 18% higher nDCG, 14% higher precision, and 35% lower recall. To ensure a fair comparison, we adjusted LensKit's nDCG calculation to match RecBole's method. This alignment made the performance more comparable, with LensKit achieving an nDCG of 0.2540 and RecBole 0.2674. Differences in similarity matrix calculations were identified as the main cause of performance deviations. After modifying LensKit to retain only the top K similar items, both libraries showed nearly identical nDCG values across all data sets. For instance, both achieved an nDCG of 0.2586 on the ML-1M data set with the same random seed. Initially, LensKit's original implementation only surpassed RecBole in the ModCloth dataset.
We went through thousands of tech deals and these are the best Amazon Prime Day deals under 50
On the second day of Amazon's Prime Day sale, the deals on smaller gadgets and accessories are still going strong. In fact, as I was checking to make sure these deals were still live, I noted about five on the list that dropped a few dollars cheaper than they were yesterday. As a reminder, this list represents the best of the affordable tech gear that we at Engadget have tested, reviewed and know to be worth your time. Everything here is on sale for 49.99 or under to make up the best possible roundup of the Prime Day tech deals you can get for under 50. As with all Engadget tech deals coverage, we only highlight discounts on gear we've tested or have otherwise used and know to be worthy of your money. We cross-checked our guides and reviews with the Prime Day deals Amazon has put forth to come up with what you see here. The Anker Nano power bank in black is on sale for Prime Day for 16.13. That's a 15 percent discount and a good deal for one of the best power banks we tested. We like the foldable USB-C connector which means you don't have to remember a separate cable and the amount of charge it delivers for such a small package. Plus it's compact enough you can use it while it refills your phone.
Five most exciting new changes coming in Apple's huge iPhone update - including controversial 'cheater's paradise' feature
Apple's new iOS update is just weeks away - and more details are starting to emerge about what is shaping up to be the biggest update yet. Originally announced at the company's annual Worldwide Developers Conference (WWDC) in June, the software is expected to hit devices in mid-September. Apple is touting its AI integration with iOS 18, iPadOS 18, and macOS Sequoia - called'Apple Intelligence' - as the update's flagship feature. The feature will bring a lot of change to the operating system, including new-and-improved Siri capabilities, the ability to create custom emojis, and more. But the change that made headlines most was a new app-hiding feature dubbed'cheater's paradise' because it allows people to conceal certain apps (like dating apps, for instance) in locked folders.
We went through thousands of tech deals and these are the best Amazon Prime Day deals under 50 that we could find
Amazon Prime Day covers deals across every department but at Engadget, we focus mainly on discounts on the tech we've tested and recommend. As you may notice when browsing day two of Amazon's sale, a lot of the tech gear is still pretty pricey -- even after the discounts. So, as an antidote, we went through every tech deal out there and found the affordable Prime Day deals on the accessories and smaller gadgets that we recommend. Here are the best Prime Day tech deals under 50. As with all Engadget tech deals coverage, we only highlight discounts on gear we've tested or have otherwise used and know to be worthy of your money. We cross-checked our guides and reviews with the Prime Day deals Amazon has put forth to come up with what you see here. The Anker Nano power bank in black is on sale for Prime Day for 16.13. That's a 15 percent discount and a good deal for one of the best power banks we tested. We like the foldable USB-C connector which means you don't have to remember a separate cable and the amount of charge it delivers for such a small package.
Prime Day tech deals under 25 that we've tested and approved
Don't fret if you missed out on day one of Amazon Prime Day -- there are still tons of deals to be had during the final day today. Prime Day deals have discounted plenty of our favorites this year, including a bunch of affordable tech that's now even cheaper thanks to the shopping event. We've sifted through all of the junk to find all of the tech deals under 25 that are actually worth your money. As a reminder (and for the uninitiated): Engadget treats tech deals with the same care as we would "regular" tech news. When we scour the web for deals, we're looking not only for the best prices possible, but also the best products as well.
The Real Problem With TikTok's 'Fruity' Boy Trend
Cruise around TikTok these days and you're bound to stumble on one: A young woman, standing next to a presumed beau, pointing out their "feminine, vintage-Levi's-wearing, tote-bag-carrying, mustached little boyfriend." If you haven't seen one of those, maybe it's the person saying "if my friends think you're a little bit fruity" then you're their type. Keep scrolling and you'll see commenters saying they're "manifesting my little gay boyfriend." Earlier this month, a piece in Dazed explained the trend thus: "Fruity boys" are "the new soft boys." The slang term, the latest in a long line of similar monikers going back to "metrosexual," aims to identify a new archetype: a man who is usually straight who possesses a set of nebulously feminine or queerish qualities, or a "zesty aura."
Cool It With The Prime Day Air Conditioners and Fans (2024)
Millions of Americans are currently dealing with a heat wave across the US, so staying cool is important. There are many ways to deal with the scorching heat, and the good news is that quite a few of the tools that can help are on sale for Prime Day. These range from the obvious Prime Day air conditioner and tower fan deals, but you can also find discounted cooling sheets and even a mattress that can help transfer your body heat during the night for better sleep if you are in fact sleeping and not obsessively tracking our Prime Day liveblog. We test products year-round and handpicked these deals. We'll update this guide periodically throughout the sale event.
The 289 Best Prime Day Deals and Biggest Discounts On Our Favorite Gadgets
WIRED's coverage of the best Amazon Prime Day deals and biggest discounts is, as they say, built different. For starters, we only include products someone from our team has personally tested and reviewed. That means you will not find flimsy fad gadgets or shoddy dupes among our recommendations. What remains is all solid stuff. You'll often find a link to a longer write-up to a review or buying guide if you want to make a fully informed buying decision. Additionally, we obsessively track prices to make sure everything on the list is a genuinely good price right now. For more on that, consult our helpful guide to shopping like a pro on Prime Day. Today is the last day of Prime Day, so you might not see some of these deals until Amazon's second Prime Day event in October or Black Friday in November. We test products year-round and handpicked these Prime Day deals. Products that are sold out or no longer discounted will be crossed out. We'll update this guide regularly throughout Prime ...