The use of Recommender Systems in web technology and an in-depth analysis of Cold State problem

Denis Selimi; Krenare Pireva Nuci

Home/Archive/arXiv

arXiv · 2009.04780

The use of Recommender Systems in web technology and an in-depth analysis of Cold State problem

Denis Selimi·Krenare Pireva Nuci

View original source ↗Read source document ↗Export metadata ↓

Abstract

In the WWW (World Wide Web), dynamic development and spread of data has resulted a tremendous amount of information available on the Internet, yet user is unable to find relevant information in a short span of time. Consequently, a system called recommendation system developed to help users find their infromation with ease through their browsing activities. In other words, recommender systems are tools for interacting with large amount of information that provide personalized view for prioritizing items likely to be of keen for users. They have developed over the years in artificial intelligence techniques that include machine learning and data mining amongst many to mention. Furthermore, the recommendation systems have personalized on an e-commerce, on-line applications such as Amazon.com, Netflix, and Booking.com. As a result, this has inspired many researchers to extend the reach of recommendation systems into new sets of challenges and problem areas that are yet to be truly solved, primarily a problem with the case of making a recommendation to a new user that is called cold-state (i.e. cold-start) user problem where the new user might likely not yield much of information searched. Therfore, the purpose of this paper is to tackle the said cold-start problem with a few effecient methods and challenges, as well as identify and overview the current state of recommendation system as a whole

Explore related subjects

cs.IR cs.AI

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Denis Selimi, Krenare Pireva Nuci. 2020-09-10. The use of Recommender Systems in web technology and an in-depth analysis of Cold State problem. https://arxiv.org/abs/2009.04780

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Component Benchmark: Hierarchical Model Profiling for Large-scale Recommendation Systems

Large-scale recommendation models pose distinct, under-explored profiling challenges. Most recommendation model architectures are structurally heterogeneous, intermixing memory-bandwidth-bound operations, small compute-bound dense layers, dynamic shapes from jagged categorical features, and low-arithmetic-intensity operations. Recommendation models evolve rapidly as modeling engineers experiment with compositions, often written without visibility into hardware execution characteristics. Standard profiling tools offer either end-to-end throughput or operator-level traces, but cannot attribute performance to the submodules that practitioners reason about. We present Component Benchmark (CB), a profiling system that independently characterizes each submodule performance in a hierarchical manner, providing a tree-structured, interactive visualization that brings performance clarity to ML practitioners. At its core, CB provides a simple yet extensible, submodule-based benchmarking framework with a plugin architecture that enables hierarchical performance analysis. These large-scale recommendation models are TB-scale, run on thousands of GPUs and ingest 100B examples per day. We demonstrate CB's effectiveness on common open sourced models and discuss how CB has been leveraged to accelerate modern recommendation model performance analysis and optimization.

cs.IR↗

arXiv2026

Recommendation World Models for Future-State Control

Sequential recommendation optimizes which items to rank, while each displayed slate also shapes subsequent feedback and user state. We study how a trained ranker can support decisions about these future consequences. We introduce UA-TWM, a utility-anchored world-model interface that constructs nearby slate actions, estimates their target-relevant consequences, and selects an alternative subject to utility constraints. The reference slate serves as a fallback when no alternative qualifies. A logged-replay instantiation combines utility and target-gain estimates with calibrated failure-risk prediction; a closed-loop instantiation uses one-step state-action prediction and updates its decisions after observed feedback. We evaluate transfer across twelve sequential backbones on MovieLens-25M and KuaiRand-Pure, and repeated target-directed interaction in KuaiSim. Attaching the interface improves Recall@20, NDCG@20, and future-state alignment for every matched logged backbone. Selection ablations reveal the utility and risk costs of aggressive target pursuit, while closed-loop diagnostics isolate the contribution of action-conditioned prediction. Local consequence modeling thus enables target-aware selection around a trained sequential ranker.

cs.IR↗

arXiv2026

RecToolBench: Benchmarking Recommendation-Specific Tool Orchestration under Fuzzy User Intent

Recent advances in agentic recommender systems are shifting recommender systems from passive filtering engines to instruction-following agents that use external tools to resolve user intent. However, existing benchmarks often assume explicit user intent, simplified tool environments, or isolated function calls, leaving realistic tool orchestration for recommendation underexplored. To bridge this gap, we propose RecToolBench, a Model Context Protocol (MCP)-based benchmark for evaluating tool-using recommender agents under fuzzy user instructions. RecToolBench contains more than 1,200 executable tasks across three recommendation domains, 13 MCP servers, and 32 tools, spanning single-tool calls, parallel tool calls, sequential tool chains, and hybrid tool orchestration. We construct RecToolBench with a scalable synthesize--fuzzify--judge pipeline that generates executable fuzzy recommendation tasks, and evaluates agent trajectories using rule-based execution checks and rubric-based LLM evaluation. Experiments on representative LLMs show that syntactically valid tool calls do not guarantee successful recommendations. Models struggle with semantic parameter grounding, multi-step evidence integration, and grounded final recommendations, especially as orchestration complexity increases. Our results identify tool orchestration under fuzzy user intent as a major bottleneck for agentic recommender systems. Our data and code are available at https://github.com/ShawnChenn/RecToolBench.

cs.IR↗