000			03846nam a2200529 i 4500
001			9198868
003			IEEE
005			20220712204954.0
006			m o d
007			cr |n|||||||||
008			201113s2020 mau ob 001 eng d
019			_a1159803313
020			_a9780262358798 _qelectronic bk.
020			_z0262358794 _qelectronic bk.
020			_z9780262539074
020			_a0262358786
020			_z0262539071
020			_z9780262358781 _qelectronic bk.
028	0	2	_aEB00811221 _bRecorded Books
035			_a(CaBNVSL)mat09198868
035			_a(IDAMS)0b0000648d0883d1
040			_aCaBNVSL _beng _erda _cCaBNVSL _dCaBNVSL
050		4	_aZA3084 _b.S37 2020eb
082	0	4	_a025.04 _223
100	1		_aSchrage, Michael, _eauthor. _925958
245	1	0	_aRecommendation engines / _cMichael Schrage.
264		1	_aCambridge, Massachusetts : _bThe MIT Press, _c2020.
264		2	_a[Piscataqay, New Jersey] : _bIEEE Xplore, _c[2020]
300			_a1 PDF.
336			_atext _2rdacontent
337			_aelectronic _2isbdmedia
338			_aonline resource _2rdacarrier
490	1		_aThe MIT Press essential knowledge series
504			_aIncludes bibliographical references and index.
506			_aRestricted to subscribers or individual electronic text purchasers.
520			_a"How does Netflix know just what to suggest you watch next? How does Amazon determine what a "customer like you" has also purchased? The answer is recommender systems, the technological concept that lies at the heart of most of the successful companies in the digital economy. Michael Schrage starts with the origins of recommender systems, which go back further than you think (see: the Oracle at Delphi for one of history's earliest recommenders), and a history of the first companies to harness recommendations. He then discusses the technology behind how recommenders work: the AI and machine learning algorithms that power these recommender platforms. Next he discusses the role of user experience, and how recommender systems are designed, and how design choices function as nudges to make certain recommendations more salient than others. He explores three case studies: Spotify, Bytedance, and Stitch Fix, looking at how recommenders can create new business solutions and how algorithms can go beyond curation to content creation. The concluding chapter on the future of recommender systems is perhaps the most enlightening. Moving away from technology and business, Schrage embraces the philosophical, probing the role of free will in a world mediated by recommender systems (a recommendation inherently offers a choice; without the element of choice, any digital manipulation of our preferences cannot truly be called a "recommendation"), and exploring the role of recommender systems as a means of improving the self. In the vein of Free Will, this book presents the essential information while revealing the author's point of view. Schrage wants to push our understanding of recommender systems beyond the technological, to understand what societal role they play and what opportunities they offer now and in the future"-- _cProvided by publisher.
530			_aAlso available in print.
538			_aMode of access: World Wide Web
650		0	_aRecommender systems (Information filtering) _99125
655		4	_aElectronic books. _93294
710	2		_aIEEE Xplore (Online Service), _edistributor. _925959
710	2		_aMIT Press, _epublisher. _925960
776	0	8	_iPrint version: _aSchrage, Michael. _tRecommendation engines. _dCambridge, Massachusetts : The MIT Press, 2020 _z9780262539074 _w(DLC) 2019042167 _w(OCoLC)1131884428
830		0	_aMIT Press essential knowledge series. _925961
856	4	2	_3Abstract with links to resource _uhttps://ieeexplore.ieee.org/xpl/bkabstractplus.jsp?bkn=9198868
942			_cEBK
999			_c73650 _d73650