Matches in SemOpenAlex for { <https://semopenalex.org/work/W2004051715> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2004051715 abstract "Decision trees have been used for several decades as simple and effective solutions to supervised learning problems. Their success extends to tasks across a variety of areas. Yet, data collected today through web-domains such as on-line advertising presents many new challenges: sheer size, the prevalence of high-arity categorical features, unknown feature-values, cold starts, sparse training instances, and imbalance in the class labels. We argue that decision trees remain an ideal choice for applications of on-line advertising as they naturally construct higher-order conjunctive features; we then contribute two ideas to improve tree-building accordingly. First, to handle high-arity categorical features, we introduce a method to cluster feature-values based on their output responses. The result is more data-dense trees with relatively small branching factors. Second, we employ cross-validation as a principled approach to derive splitting and stopping criteria: thereby we identify splits that generalize well, and also curb overfitting. Evaluated on three distinct probability-estimation tasks in on-line advertising, our method, CCDT, shows significant improvements in the accuracy of prediction." @default.
- W2004051715 created "2016-06-24" @default.
- W2004051715 creator A5003101801 @default.
- W2004051715 creator A5038200034 @default.
- W2004051715 creator A5044522151 @default.
- W2004051715 date "2014-11-03" @default.
- W2004051715 modified "2023-09-27" @default.
- W2004051715 title "On Building Decision Trees from Large-scale Data in Applications of On-line Advertising" @default.
- W2004051715 cites W1509515766 @default.
- W2004051715 cites W1601142477 @default.
- W2004051715 cites W1780185704 @default.
- W2004051715 cites W1969675113 @default.
- W2004051715 cites W1970210633 @default.
- W2004051715 cites W1990381576 @default.
- W2004051715 cites W1990777911 @default.
- W2004051715 cites W2008183828 @default.
- W2004051715 cites W2009708807 @default.
- W2004051715 cites W2012905273 @default.
- W2004051715 cites W2018049374 @default.
- W2004051715 cites W2020663993 @default.
- W2004051715 cites W2023163512 @default.
- W2004051715 cites W2043779491 @default.
- W2004051715 cites W2070996757 @default.
- W2004051715 cites W2073358075 @default.
- W2004051715 cites W2093217068 @default.
- W2004051715 cites W2098824882 @default.
- W2004051715 cites W2112651261 @default.
- W2004051715 cites W2141014056 @default.
- W2004051715 cites W2149706766 @default.
- W2004051715 cites W2173213060 @default.
- W2004051715 cites W2787894218 @default.
- W2004051715 cites W2791559636 @default.
- W2004051715 cites W2911964244 @default.
- W2004051715 cites W3100094457 @default.
- W2004051715 cites W3106889297 @default.
- W2004051715 cites W3125937743 @default.
- W2004051715 doi "https://doi.org/10.1145/2661829.2662044" @default.
- W2004051715 hasPublicationYear "2014" @default.
- W2004051715 type Work @default.
- W2004051715 sameAs 2004051715 @default.
- W2004051715 citedByCount "4" @default.
- W2004051715 countsByYear W20040517152016 @default.
- W2004051715 countsByYear W20040517152017 @default.
- W2004051715 countsByYear W20040517152019 @default.
- W2004051715 crossrefType "proceedings-article" @default.
- W2004051715 hasAuthorship W2004051715A5003101801 @default.
- W2004051715 hasAuthorship W2004051715A5038200034 @default.
- W2004051715 hasAuthorship W2004051715A5044522151 @default.
- W2004051715 hasConcept C124101348 @default.
- W2004051715 hasConcept C198352243 @default.
- W2004051715 hasConcept C205649164 @default.
- W2004051715 hasConcept C2522767166 @default.
- W2004051715 hasConcept C2524010 @default.
- W2004051715 hasConcept C2778755073 @default.
- W2004051715 hasConcept C33923547 @default.
- W2004051715 hasConcept C41008148 @default.
- W2004051715 hasConcept C58640448 @default.
- W2004051715 hasConcept C84525736 @default.
- W2004051715 hasConceptScore W2004051715C124101348 @default.
- W2004051715 hasConceptScore W2004051715C198352243 @default.
- W2004051715 hasConceptScore W2004051715C205649164 @default.
- W2004051715 hasConceptScore W2004051715C2522767166 @default.
- W2004051715 hasConceptScore W2004051715C2524010 @default.
- W2004051715 hasConceptScore W2004051715C2778755073 @default.
- W2004051715 hasConceptScore W2004051715C33923547 @default.
- W2004051715 hasConceptScore W2004051715C41008148 @default.
- W2004051715 hasConceptScore W2004051715C58640448 @default.
- W2004051715 hasConceptScore W2004051715C84525736 @default.
- W2004051715 hasLocation W20040517151 @default.
- W2004051715 hasOpenAccess W2004051715 @default.
- W2004051715 hasPrimaryLocation W20040517151 @default.
- W2004051715 hasRelatedWork W1996490503 @default.
- W2004051715 hasRelatedWork W2029284671 @default.
- W2004051715 hasRelatedWork W2064050250 @default.
- W2004051715 hasRelatedWork W2195636112 @default.
- W2004051715 hasRelatedWork W2198623851 @default.
- W2004051715 hasRelatedWork W2335612998 @default.
- W2004051715 hasRelatedWork W2363273833 @default.
- W2004051715 hasRelatedWork W2760986417 @default.
- W2004051715 hasRelatedWork W3010840919 @default.
- W2004051715 hasRelatedWork W3033096792 @default.
- W2004051715 isParatext "false" @default.
- W2004051715 isRetracted "false" @default.
- W2004051715 magId "2004051715" @default.
- W2004051715 workType "article" @default.