cold start problem
In plain wordsThe trouble a recommendation system has with brand-new users or items: with no history to learn from, it has little basis for good suggestions.
The difficulty of making good predictions for users, items or whole systems that have little or no interaction history. It is most acute for collaborative filteringcollaborative filtering, n.: Recommending things based on what people with similar tastes liked, without needing to know anything about the things themselves, as in 'people who bought this also bought…'., which relies entirely on past behavior, and takes three forms: new users, with no history from which to infer preferences; new items, which nobody has interacted with and which therefore are never recommended and never gather data; and new systems, with too few interactions overall. Remedies include onboarding questions, popularity or demographic defaults, content-basedcontent-based filtering, n.: Recommending items that resemble what you already liked, judged by the items' own features, such as a film's genre, cast and plot, rather than by other people's choices. and hybrid models that use item attributes and pretrained embeddingsembedding, n.: A list of numbers that stands for a word, picture or other item, arranged so that similar items get similar lists. It lets a computer measure similarity of meaning as distance., side information such as context or social links, transfer learningtransfer learning, n.: Reusing what a model learned on one task to get a head start on another — like a pianist picking up the organ faster than a beginner. It lets models learn new jobs from little data. from other domains, meta-learningmeta-learning, n.: Training a system across many different tasks so that it gets better at learning itself, letting it pick up a new task quickly from only a few examples. for fast per-user adaptation, and deliberate exploration with banditmulti-armed bandit, n.: A puzzle named after a gambler choosing between slot machines: you must keep picking among options whose payoffs are unknown, learning which is best while wasting as few tries as possible on the others. algorithms that show uncertain items to gather evidence. The term is also used loosely for any model that must perform before data accumulate.
To beat the cold start problem, new sellers' listings get a guaranteed exploration slot during their first week.
Origin
The phrase borrows the image of starting an engine from cold. It was in use in recommender research by the early 2000s, and the SIGIR 2002 paper 'Methods and Metrics for Cold-Start Recommendations' by Andrew Schein and colleagues helped standardize it.
Related
- recommender systemrecommender system, n.: Software that guesses which songs, products, posts or jobs you are most likely to want and shows those first, as when a video app lines up the next clip or a shop suggests an add-on.
- collaborative filteringcollaborative filtering, n.: Recommending things based on what people with similar tastes liked, without needing to know anything about the things themselves, as in 'people who bought this also bought…'.
- content-based filteringcontent-based filtering, n.: Recommending items that resemble what you already liked, judged by the items' own features, such as a film's genre, cast and plot, rather than by other people's choices.
- multi-armed banditmulti-armed bandit, n.: A puzzle named after a gambler choosing between slot machines: you must keep picking among options whose payoffs are unknown, learning which is best while wasting as few tries as possible on the others.
- meta-learningmeta-learning, n.: Training a system across many different tasks so that it gets better at learning itself, letting it pick up a new task quickly from only a few examples.
- implicit feedbackimplicit feedback, n.: Clues about what people like that come from what they do, such as clicking, buying, watching or skipping, rather than from ratings or reviews they deliberately give.
Sources
- Schein, A. I., Popescul, A., Ungar, L. H. & Pennock, D. M. (2002). Methods and Metrics for Cold-Start Recommendations. Proc. ACM SIGIR 2002.
Mentioned in
recommender systemrecommender system, n.: Software that guesses which songs, products, posts or jobs you are most likely to want and shows those first, as when a video app lines up the next clip or a shop suggests an add-on., collaborative filteringcollaborative filtering, n.: Recommending things based on what people with similar tastes liked, without needing to know anything about the things themselves, as in 'people who bought this also bought…'., content-based filteringcontent-based filtering, n.: Recommending items that resemble what you already liked, judged by the items' own features, such as a film's genre, cast and plot, rather than by other people's choices., generative recommendationgenerative recommendation, n.: A newer approach to recommendation that uses language-model-style AI to predict the next item a person will want, one step at a time, much as a chatbot predicts the next word.