Corpus ID: 36698509

Using Human and Machine Processing in Recommendation Systems

@inproceedings{Colson2013UsingHA,
  title={Using Human and Machine Processing in Recommendation Systems},
  author={Eric Colson},
  booktitle={HCOMP},
  year={2013}
}
This paper presents a case study of an online apparel retailer called Stitch Fix, which uses both machine and human processing in its recommendation system. 

Topics from this paper

Requirements Engineering for General Recommender Systems Ivens Portugal
TLDR
A systematic review has been conducted to identify the type of user and recommendation data items needed by a general recommender system, and a user and item model is proposed. Expand
Feature Selection and Validation for Human Classifiers
Algorithmic approaches to prediction and recommendation can often be improved by combining the results with the curation of human experts. Hybrid machinehuman recommendation systems can combine theExpand
Human computation for constraint-based recommenders
TLDR
An overview of the PeopleViews environment is provided and it is shown how recommendation knowledge can be collected from users of the environment on the basis of micro-tasks and how the system exploits this knowledge for automatically generating recommendation knowledge bases. Expand
Requirements Engineering for General Recommender Systems
TLDR
A systematic review has been conducted to identify the type of user and recommendation data items needed by a general recommender system, and a user and item model is proposed. Expand
Deep Learning-based Intelligent Preferred Fashion Recommendation using Implicit User Profiling
In the massive online fashion market, it is not easy for consumers to find the fashion style they want by keyword search for their preferred style. It can be resolved into consumer needs basedExpand
Towards Minimizing e-Commerce Returns for Clothing
TLDR
The research project Think!First tackles problems in freight mobility by using an unique combination of gamification elements, persuasive design principles and machine learning, and presents a slightly modified rule learning algorithm that always characterizes a given class (here: returns). Expand
Manipulating and Measuring Model Interpretability
TLDR
A sequence of pre-registered experiments showed participants functionally identical models that varied only in two factors commonly thought to make machine learning models more or less interpretable: the number of features and the transparency of the model (i.e., whether the model internals are clear or black box). Expand
Ranking Images Based on Aesthetic Qualities
TLDR
A novel approach for learning image representation based on qualitative assessments of visual aesthetics that relies on a multi-node multi-state model that represents image attributes and their relations and it has demonstrated a high performance rate in ranking fashion images. Expand

References

SHOWING 1-3 OF 3 REFERENCES
Information seeking: convergence of search, recommendations, and advertising
How to address user information needs amidst a preponderance of data.
Answering Queries using Humans, Algorithms and Databases
TLDR
The design of the first declarative language involving human-computable functions, standard relational operators, as well as algorithmic computation is described, which can act as a roadmap for new area of data management research where human computation is routinely used in data analytics. Expand
CrowdScreen: algorithms for filtering data with humans
TLDR
Deterministic and probabilistic algorithms to optimize the expected cost (i.e., number of questions) and expected error and can form an integral part of any query processor that uses human computation. Expand