MARC details
| 000 -LEADER |
|---|
| fixed length control field |
09227nam a22002537a 4500 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION |
|---|
| fixed length control field |
201210b2023 a|||f bm|| 00| 0 eng d |
| 040 ## - CATALOGING SOURCE |
|---|
| Original cataloging agency |
EG-CaNU |
| Transcribing agency |
EG-CaNU |
| 041 0# - Language Code |
|---|
| Language code of text |
eng |
| Language code of abstract |
eng |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER |
|---|
| Classification number |
610 |
| 100 0# - MAIN ENTRY--PERSONAL NAME |
|---|
| Personal name |
Mohamed Reda Zohair Ali Bennawy |
| 245 1# - TITLE STATEMENT |
|---|
| Title |
Real-Time Stream Processing For Recommendation Engine(s)/ |
| Statement of responsibility, etc. |
Mohamed Reda Zohair Ali Bennawy |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. |
|---|
| Date of publication, distribution, etc. |
2023 |
| 300 ## - PHYSICAL DESCRIPTION |
|---|
| Extent |
75 p. |
| Other physical details |
ill. |
| Dimensions |
21 cm. |
| 500 ## - GENERAL NOTE |
|---|
| Materials specified |
Supervisor: <br/>Walid Al-Atabany |
| 502 ## - Dissertation Note |
|---|
| Dissertation type |
Thesis (M.A.)—Nile University, Egypt, 2023 . |
| 504 ## - Bibliography |
|---|
| Bibliography |
"Includes bibliographical references" |
| 505 0# - Contents |
|---|
| Formatted contents note |
Contents:<br/>List of Abbreviations.................................................................................................................. i<br/>List of Tables............................................................................................................................. ii<br/>List of Figures .......................................................................................................................... iii<br/>Chapter 1: Introduction...............................................................................................................1<br/>1.1 Motivation ........................................................................................................................1<br/>1.2 Problem Statement ...........................................................................................................1<br/>1.3 User Stories ......................................................................................................................2<br/>1.4 Challenges........................................................................................................................3<br/>1.5 Summary of Contributions...............................................................................................3<br/>1.6 Thesis Outline...................................................................................................................4<br/>Chapter 2: Literature Survey ......................................................................................................5<br/>2.1 Introduction ......................................................................................................................5<br/>2.2. Data Architecture ............................................................................................................6<br/>2.3 Use Cases .........................................................................................................................9<br/>2.4 Frameworks....................................................................................................................12<br/>2.5 Comparison ....................................................................................................................22<br/>2.6 Architecture ....................................................................................................................24<br/>2.6.1 Benefits of modern stream processing architecture .................................................25<br/>2.7 Session-based Recommender Systems...........................................................................26<br/>2.8 Evaluation of any recommender system:........................................................................27<br/>2.8.1 A/B Testing..............................................................................................................27<br/>2.8.2 Rating Prediction Accuracy .....................................................................................28<br/>2.8.3 Ranking Measures....................................................................................................29<br/>2.8.4 Hit Rates Measures..................................................................................................30<br/>2.8.5 Diversity Measures..................................................................................................31<br/>2.9 Recommender Model Types...........................................................................................32<br/>2.9.1 Content-Based Recommender System.....................................................................33<br/>2.9.2 Collaborative Filtering Recommender System........................................................34<br/>Chapter 3: Methodology...........................................................................................................42<br/>3.1 Introduction ....................................................................................................................42<br/>3.2 E-Tourism Datasets........................................................................................................42<br/>3.3 Trivago Dataset Description...........................................................................................43<br/>3.3.1 Overview..................................................................................................................43<br/>3.3.2 Files Description ......................................................................................................46<br/>3.3.3 Descriptive Analysis................................................................................................46<br/>Chapter 4: Results and Discussions..........................................................................................52<br/>4.1 Experiments....................................................................................................................52<br/>4.2 Evaluation Metrics .........................................................................................................52<br/>4.3 Experiments....................................................................................................................53<br/>4.4 Benchmarks....................................................................................................................53<br/>4.5 Proposed Solution...........................................................................................................56<br/>Chapter 5: Conclusions and Future Work ................................................................................58<br/>5.1 Conclusion......................................................................................................................58<br/>5.2 Future directions.............................................................................................................59<br/>References................................................................................................................................6 |
| 520 3# - Abstract |
|---|
| Abstract |
Abstract:<br/>Event stream processing (ESP) is a data processing methodology which tackle online <br/>processing for a variety of events. Recently stream processing witnessed a huge <br/>interest in both academic research and corporate use cases. As a consequence, for the <br/>extremely huge data sources recently generated and diversely of usage. Data sources <br/>vary from websites logs, social media feeds, news articles, internal business <br/>transactions, IoT devices logs, ... etc. Academically, a lot of research papers discuss <br/>how to deal with enormous cloud of events in real-time with different data structures <br/>such as text, video, logs, transactions, … etc. Aside with, highlighting the weakness <br/>and strength points of the streaming platforms technologies. From corporate point of <br/>view, decision makers ask about how to best utilize those events with minimal delay <br/>in order to 1) uncover insights in real-time, 2) mine textual events, 3) recommend <br/>decisions. This requires a mix of machine learning, stream processing technologies <br/>and modern architecture to achieve best utilization with low latency. Unfortunately, <br/>each technology is typically optimized independently therefore, it is a challenge to <br/>combine all technologies together and have a scalable real-world application. <br/>Through the thesis, we shall discuss the state-of-the-art event stream processing <br/>technologies by summarizing definitions, data flow architectures, use cases, <br/>frameworks, and architecture best practices Also, we propose a recommendation <br/>engine architecture to perfectly cope with a real-life data stream in the E-Tourism <br/>domain.<br/>The Association for Computing Machinery ACM recommendation systems challenge <br/>(ACM RecSys) [1] released an e-tourism dataset for the first time in 2019. Challenge <br/>shared hotel booking sessions from the trivago website asking to rank the hotel`s list <br/>for the users. The better ranking should achieve a high click-out rate. We introduce a<br/>state of art architecture and a session-based recommender system on top of portal <br/>streaming data. Proposed solution take into consideration both recommendation <br/>engine accuracy and a low latency architecture. Compared to different benchmark <br/>publications on same dataset, proposed solution outperform in time with 10x faster <br/>using only 2% of computational power used. Paper shared the architecture and <br/>recommendation engine into details taking into consideration the ability to deploy the<br/>model into real-life production environments. |
| 546 ## - Language Note |
|---|
| Language Note |
Text in English, abstracts in English and Arabic |
| 650 #4 - Subject |
|---|
| Subject |
Informatics-IFM |
| 655 #7 - Index Term-Genre/Form |
|---|
| Source of term |
NULIB |
| focus term |
Dissertation, Academic |
| 690 ## - Subject |
|---|
| School |
Informatics-IFM |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) |
|---|
| Source of classification or shelving scheme |
Dewey Decimal Classification |
| Koha item type |
Thesis |
| 650 #4 - Subject |
|---|
| -- |
266 |
| 655 #7 - Index Term-Genre/Form |
|---|
| -- |
187 |
| 690 ## - Subject |
|---|
| -- |
266 |