PDF FILE INDEX: Chinese => p. 5; Japanese => p. 9 

【English】【2020.07.03 updated】

Profile 00 00@2x

Ting-Rui(Ray) Chen

I acquired the Master Degree of Computer Science at National Central University in 2019. I major in researching Deep Learning(Data-Driven models) in the period of master course. My thesis is about clickstream behavioral modeling. We build a service for collecting user online behavior. I also research the stock price prediction. In the period of acquiring Master degree, I have experience on processing Million-scale data and speeding up the procedure from 3 days to 3 hours and building a service from zero.

I joined Pinkoi on December 2019 and had been laid off by Pinkoi since April 2020 because the COVID-19 let Pinkoi need to downsize. In the 4 months at Pinkoi, I refactored the code repository for speed up data pipeline development , which make data team care less when building new data pipeline and fetch data more efficiency. I re-launched the projects about search-bar autocomplete system which data pipeline was down for several months and brand-suggestion system which was down for more than 3 years. I re-work the search-bar autocomplete system in the latest code style and keep the performance as before. The brand-suggestion system was finished in latest code style, too. However, I tune the performance of the brands' coverage from ~1500 up to ~11000 brands(~15000 brands in total).


Headline
Ex Data Engineer @ Pinkoi.com


+886 988555373
[email protected]


Skills

  • Python (PySpark, PyFlink, Keras, PyTorch, flask, sci-kit learn, …etc.) 
  • Elasticsearch(Python api, Python DSL api)
  • SQL (MySQL) 
  • Apache Airflow (Local or GCP Composer)
  • Javascript (jQuery, Vue.js)
  • HTML5
  • Cloud Computing Platform(Heroku, AWS ElasticBeantalk, GCP BQ, DataProc, DataFlow, Pub/Sub,..., etc.);
  • C/C++


Licenses & Certifications

  • JLPT N2
  • Collegiate Programming Examination(CPE) - Professional(Ranking:176 / 2044(8.6%))[Proficient with fundamental algorithms and data structures, and possessing good programming ability.] 


About

        I acquired the Master Degree of Computer Science at Nation Central University on July 2019. For my thesis, I built a system include front-end and back-end to serve user with visualize personal data and collect user behavior as background target. Finally, we analyzed the user behavior in the collected data.
        Before I start to involve to my thesis, from March to June 2018, I participated in the data competition held by Trend Micro. We won the 7th place in the 487 team competition. In July 2018, I applied for an intern job in Industrial Technology Research Institute(ITRI) with score of the competition. I worked on Business AI model development in Big Data Center for two months.

        I joined Pinkoi.com on December 2019 and I have been laid off by Pinkoi since April 2020 because the COVID-19 let Pinkoi.com need to downsize. In the 4 months at Pinkoi, I refactored the code repository for speed up data pipeline development , which make data team care less when building new data pipeline and fetch data more efficiency. I re-launched the projects about search-bar autocomplete system which data pipeline was down for several months and brand-suggestion system which was down for more than 3 years. I re-work the search-bar autocomplete system in the latest code style and keep the performance as before. The brand-suggestion system was finished in latest code style, too. However, I tune the performance of the brands' coverage from ~1500 up to ~11000 brands(~15000 brands in total).

Experience

Pinkoi.com,Data Engineer,Dec 2019 – Apr 2020, 4 mos

Routine works are maintaining ETL pipeline, responding the data request from other teams(BI, UX ... etc.)


Key Achievement:

  1. Refactor Code repository and fix up several issues: Make teammate develop more efficiency than before about 10% fast and more readable than before about 50%.
  2. Search-bar autocomplete system: refactored in new data pipeline and make it renew everyday while keeping the system performance.
  3. Search-bar brand-suggestion system: redesign it by using association rules for cleaning the user behavior and merging the brand list to maximized the recall. Finally, tuned the performance of the brands' coverage from ~1500 up to ~11000 brands.


National Central University,Mar 2017 – Jul 2019,2 yrs 5 mos

Researching Assistant — Mar 2017 – Jul 2019,Data Analytics Research Team

         Server Management, Homepage design and development, and Database Management

Teaching Assistant — Feb 2018 – Jan 2019 

         Statistical Learning, Sep 2018 - Jan 2019
         Computer Organization, Feb 2018 - Jun 2018

Industrial Technology Research Institute(ITRI),Intern,Jul 2018 – Aug 2018,2 mos

Business Application Analysis Technology Department of Huge Data Center

Works Applications Co., Ltd.,,Intern,Jul 2017,1 mo

Design and Develop ERP system for global coffee shop.

National Changhua University of Education,Feb 2015 – Jun 2017,2 yrs 5 mos

Teaching Assistant — Feb 2015 - Jun 2017

                 Object-Oriented-Programming, Feb 2015 - Jun 2017
                 Advanced Programming Design, Feb 2017 - Jun 2017

Bachelor Project — Jul 2015 - Jun 2016

               "A new sub-system of enrollment in college management system", Jul 2015 - Jun 2016
               "Data Migration for sub-system of club management in college management system",Jul 2015 - Feb 2016

Education

National Central University, Department of Computer Science & Information Engineering, Data Analytics Research Team- Master,Sep 2017 - Jul 2019

National Changhua University of Education, Department of Computer Science & Information Engineering — Bachelor,Sep 2013 - Jan 2017

Publications

Ting-Rui Chen, Hung-Hsuan Chen. Extended Clickstream: an analysis of the missing user behaviors in the Clickstream, 2019.

Nowadays, people often use clickstream to represent the behavior of online users. However, we found that clickstream only represents part of users' browsing behaviors. For instance, clickstream does not include tab switching and browser window switching. We collect these kinds of behaviors and named as "extended clickstream". This thesis builds a service to capture both of clickstream and extended clickstream, also provides an analysis of the differences between above. We use a Multi-Task learning model with GRU components to perform multi-objective predictions of "what kind of website the user will go next time" and "how long the interval of clicks will be" for the time series of clickstreams and extended clickstreams. Our experimental results show that combining clickstream and extended clickstream can improve the prediction performance. In addition, this article finds that the clickstream will record unintended clicks due to the operation mechanism of certain websites. Moreover, we can differentiate the single user from several devices by combining the clickstream and extended clickstream.

Ting-Rui Chen, Cheng-You Lien, Guo-Jhen Bai, Hung-Hsuan Chen. 使用者長時段跨網站瀏覽資料集之蒐集與分析 TANET '18 Taiwan Academic Network Conference, 2018.

This paper introduces a dataset containing the logs of online users’ long-term cross-website visits. Such type of open dataset is rarely-seen because collecting the logs of users’ long-term cross-website visits is difficult. As a result, opening such a dataset may help the researchers conduct advanced researches, such as online user behavior analysis, user demographical information analysis, recommender systems and online advertising system development, etc. We report the following items in this paper. First, we explain the data collecting process. Second, we show the basic statistics of this dataset. Third, we discuss the concerns to release the complete dataset. Specifically, we discuss the trade-offs between “openness” and “privacy” and our current compromising sharing policy. Fourth, we introduce experiments based on this dataset. Finally, we introduce our current plan for expanding this dataset. Keywords: online log, open data, user behavior.

Cheng-You Lien, Guo-Jhen Bai, Ting-Rui Chen, Hung-Hsuan Chen. Predicting User’s Online Shopping Tendency During Shopping Holidays. TAAI '17 Conference on Technologies and Applications of Artificial Intelligence, 2017.

The number of sales during the shopping holidays continues growing in recent years. Thus, many E-Commerce (EC) websites spend much money and effort for marketing before these shopping holidays. However, in this study we found that only part of the Internet users indeed visited the EC-websites more often than usual during the shopping holidays. Thus the increase of the sales probably comes from few individuals. Additionally, we found that users’ tendency to visit the EC websites during the shopping holiday is predictable based on simple supervised classifiers. Thus, an EC website runner can identify the potential visitors and non-visitors beforehand and apply different marketing strategy to different users.

Reference

[1]

Projects 01 00@2x
T-Brain Machine Learning Competition 2 Taiwan ETF Price Prediction Competition 7th Place (Team name: NCU_newbie)
We took the first place in the first week of the game period. Analyzing the stock price trend in the game period, we found that stock price trend is similar as historical data in the first week, however, the Taiwan stock price trend in the next three weeks goes with global economic news. Therefore, our model cannot well predict the trend. Finally, we got overall 7th place in this competition. Our models are the deep learning models. Each model gets a prediction then ensemble by a simple machine learning model as a final prediction. Our method can learned the relation from the large-scale stock price historical data, but cannot learned relation from news. As a result, we cannot well predict the trend affect by news.

[2]

I managed the progress of the team and provide my knowledge of stock market to team members. I build base learner for prediction and the ensemble learner.  In the second week of game period, we could not well predict the trend and we had no idea on parsing news to features. I suggested our team members to try everything. We set the goal to learn experience and knowledge.

Paragraph image 02 00@2x
PDF FILE INDEX:  Japanese => p. 9 

【Chinese】【2020.07.03 更新】
Profile 00 00@2x

陳廷睿 Ting-Rui(Ray) Chen

2019年7月自國立中央大學資訊工程研究所畢業取得碩士學位,在學期間主要著重學習 Deep Learning(Data-Driven models)相關技術,著重的應用有二:股市預測、使用者行為分析預測。碩士論文主要研究透過點擊流分析使用者瀏覽網路行為,我們建置了一個服務蒐集使用者的行為,並且提出擴充的資料蒐集方式以提升模型的預測性能。

2019年12月加入Pinkoi ,在 2020年4月 Pinkoi 因 COVID-19 疫情縮編,因此被 Pinkoi 資遣了。在 Pinkoi 的 4 個月裡,我對團隊共用程式碼進行了數個能提升效率的重構,加快了數據管道開發的速度,使數據團隊在構建新的數據管道時少了很多顧慮,使得獲取數據的效率更高。重構的過程中也將已停止更新數個月的搜尋欄自動補字系統及品牌推薦系統的數據管道重新啟動。在 搜尋欄自動補字系統重新加入每日更新的專案中,不但保持了原本的性能,也以團隊使用的最新 coding style 完成重構。品牌推薦系統也是以團隊使用的最新 coding style 完成的,但是我把品牌的覆蓋率從 約 1500 個品牌優化到 約11000 個品牌(總品牌數約15000個)。


目前職稱
前 Data Engineer @ Pinkoi.com


+886 988555373
[email protected]


擅長技術

  • Python (PySpark, PyFlink, Keras, PyTorch, flask, sci-kit learn, …etc.) 
  • Elasticsearch(Python api, Python DSL api) 
  • SQL (MySQL) Apache 
  • Airflow (Local or GCP Composer) 
  • Javascript (jQuery, Vue.js) 
  • HTML5 
  • Cloud Computing Platform(Heroku, AWS ElasticBeantalk, GCP BQ, DataProc, DataFlow, Pub/Sub,..., etc.) 
  • C/C++


榮譽獎項

T-Brain Machine Learning Competition 2 台灣ETF價格預測競賽 第7名 [1] 
(Team name: NCU_newbie [2])


證照


基本資料

        2017年2月我提早一學期從國立彰化師範大學資工系畢業後,申請進入了國立中央大學 資工系的 資料分析科學實驗室擔任 研究助理(2017年3月至2019年7月)以及 碩士生(2017年9月至2019年7月),並於2019年7月取得學位。在完成碩士學位論文的過程中,我從零建設了一個服務,這個服務作為瀏覽器的擴充功能在背景蒐集使用者跨網域瀏覽資料的行為,並可自動化呈現數據視覺化報表給使用者。本服務最終的使用者有150人,收集到了近千萬筆的動作紀錄。透過分析這些行為的紀錄完成了我的學位論文。
        在開始碩論之前做過的研究為「股市走勢預測」,並參加了2018年3月至6月由趨勢科技舉辦的資料競賽,我的隊伍在487隊的比賽中拿到第7名的成績;同年的 7月我以比賽的成績申請進入 台灣工業技術研究院巨量資料中心實習 兩個月,主要開發數值回歸預測的相關模型(材料用量、世界主要股市、債券)。
        目前我有兩篇被研討會接受的論文,最近的一篇是「使用者長時段跨網站瀏覽資料集之蒐集與分析」(同時公開一份資料集)被TANET '18 Taiwan Academic Network Conference, 2018. 接受;另一篇題目是「Predicting User’s Online Shopping Tendency During Shopping Holidays」被 TAAI '17 Conference on Technologies and Applications of Artificial Intelligence, 2017接受。

  2019年12月加入 Pinkoi.com,因為 COVID-19 我於 2020年4月被公司資遣。在 Pinkoi.com 的 4 個月裡,我對程式碼進行了重構,加快了數據管道開發的速度,使數據團隊在構建新的數據管道時少了很多顧慮,使得獲取數據的效率更高。重構的過程中也將已停止更新數個月的搜尋欄自動補字系統及品牌推薦系統的數據管道重新啟動。在 搜尋欄自動補字系統重新加入每日更新的專案中,不但保持了原本的性能,也以團隊使用的最新 coding style 完成重構。品牌推薦系統也是以團隊使用的最新 coding style 完成的,但是我把品牌的覆蓋率從 約 1500 個品牌優化到 約11000 個品牌(總品牌數約15000個)。

工作經歷

Pinkoi.com,Data Engineer,2019年 12月 - 2020年 4月

Routine works are maintaining ETL pipeline, responding the data request from other teams(BI, UX ... etc.) 


Key Achievement:

  1. Refactor Code repository and fix up several issues: Make teammate develop more efficiency than before about 10% fast and more readable than before about 50%. 
  2. Search-bar autocomplete system: refactored in new data pipeline and make it renew everyday while keeping the system performance. 
  3. Search-bar brand-suggestion system: redesign it by using association rules for cleaning the user behavior and merging the brand list to maximized the recall. Finally, tuned the performance of the brands' coverage from ~1500 up to ~11000 brands. 


國立中央大學,2017年 3月 - 2019年 7月

研究助理 — 2017.02 - 2019.07,協助教授進行研究(實驗室網站架設、資料庫維護、伺服器維運),協助開發資料搜集的工具。
教學助理 — 2018.02 - 2019.01

                統計學習理論,2018.09 - 2019.01,批改作業、考試。
                計算機組織,2018.02 - 2018.06,批改作業、考試。

工業技術研究院,實習生,2018年 7月 - 2018年 8月

巨量資料中心 商業應用分析技術部門 開發商業預測 AI應用。

Works Applications Co., Ltd.,,暑期實習生,2017年 7月 - 2017年 7月

日本ERP 公司的暑期實習。

國立彰化師範大學,2015年 2月 - 2017年 1月

教學助理 — 2015.02 - 2017.06

                 物件導向程式(C++)設計,2015.02 - 2017.06,批改作業、考試。
                 進階程式設計, 2017.02 - 2017.06,設定線上檢定系統,講解部分演算法。

專題 — 2015.07 - 2016.06

               「建立新的校務資訊管理系統之招生子系統」,2015.07 - 2016.06,擔任小組領導者,分配進度給專案組員,使用 OracleDB及網站技術。
               「校務資訊管理系統之社團子系統之資料轉移」,2015.07 - 2016.02,擔任專案執行者,設計解決方案將資料從MySQL DB轉移至OracleDB 8i,並確保原始程式及資料運作正常。

學歷

國立中央大學, 資訊工程研究所, 資料分析科學實驗室 - 碩士,2017 年 9 月 - 2019 年 7 月

期間負責實驗室伺服器及資料庫維運以及建設、實驗室官網製作

國立彰化師範大學, 資訊工程學系 — 學士,2013 年 9 月 - 2017 年 1 月

因符合提早畢業門檻,提早於2017年1月畢業,正常畢業時間為6月。

出版品

Ting-Rui Chen, Hung-Hsuan Chen. 擴展點擊流:分析點擊流中缺少的使用者行為, 2019.

一般認為使用者的點擊流 (clickstream) 可以代表使用者的線上瀏覽行為,然而,我們發現點擊流只能概略表示使用者的部份行為, 例如:分頁切換、視窗切換等介面間的瀏覽行為因為沒有產生與伺服器的互動,所以不會出現在點擊流或日誌 (log) 中,但使用者仍然在瀏覽網頁。 本文將這些行為收集並命名為「擴展點擊流」(extended clickstream)。 透過建設完整的系統服務並招募受試者來同步蒐集點擊流和擴展點擊流,並對兩者進行比較分析及建構深度學習模型。 我們使用含有 GRU 元件的深度學習模型,對點擊流和擴展點擊流這類型的時序資料進行「使用者下次會去什麼類型的網站」、「下次點擊會間隔多久」的多目標預測。實驗結果顯示:融合點擊流和擴展點擊流可以增進預測效能。 除此之外,本文發現點擊流會因為部分網站的運作機制而多計入了使用者沒有意圖執行的行為; 另外,我們也可以透過融合點擊流及擴展點擊流來區分出來自不同裝置的單一使用者。

Ting-Rui Chen, Cheng-You Lien, Guo-Jhen Bai, Hung-Hsuan Chen. 使用者長時段跨網站瀏覽資料集之蒐集與分析 TANET '18 Taiwan Academic Network Conference, 2018.

本文將介紹一組我們蒐集之網路使用者長時 段跨網站瀏覽紀錄資料集。使用者長時間的跨網 站紀錄 的資料不容易蒐集,且此類的開放資料集 並不常見,故此蒐集並開放本 資料集將能協助研 究者以真實資料進行 各項先進研究,如:使用者 行為分析、使用者人口特徵分析、推薦引擎及 線 上廣告 技術研發 等。 本文將包括以下部份: (1) 我 們將 說明此資料集的蒐集方式; ;(2) 我們將 報告此 資料集的基本統計資訊; ;(3) 我們將 討論公開完整 資料的顧慮,以及我們在考慮「開放」及「隱私」 這兩個矛盾的議題後所採取的妥協策略; ;(4) 我們 將介紹基於本資料集所進行的幾個實驗; ;(5) 我們 將介紹現階段擴充此資料集的計畫。

Cheng-You Lien, Guo-Jhen Bai, Ting-Rui Chen, Hung-Hsuan Chen. Predicting User’s Online Shopping Tendency During Shopping Holidays. TAAI '17 Conference on Technologies and Applications of Artificial Intelligence, 2017.

The number of sales during the shopping holidays continues growing in recent years. Thus, many E-Commerce (EC) websites spend much money and effort for marketing before these shopping holidays. However, in this study we found that only part of the Internet users indeed visited the EC-websites more often than usual during the shopping holidays. Thus the increase of the sales probably comes from few individuals. Additionally, we found that users’ tendency to visit the EC websites during the shopping holiday is predictable based on simple supervised classifiers. Thus, an EC website runner can identify the potential visitors and non-visitors beforehand and apply different marketing strategy to different users.

參照


[1]

Projects 01 00@2x

T-Brain Machine Learning Competition 2 台灣ETF價格預測競賽 第7名 (Team name: NCU_newbie)
我們在為期一個月的比賽的第一週拿到冠軍,我們分析本次比賽時期的盤勢,第一週的股市狀況是穩定的盤勢,後三週的盤勢由於國際新聞影響台灣的盤勢,導致我們的模型在後三週都無法有效預測,因此最終以總分第七名結束。我們使用的模型為深度學習模型,透過多種不同的模型進行預測,最後再以簡單的模型進行模型融合成最終的預測。我們的方法可以從大量的股市歷史數據中找出多重的相關性,但是無法讀取新聞資訊來進行相關性挖掘,因此我們在預測時沒有很好的跟上隱藏在新聞資訊的波動。

[2]

在隊伍中,我負責統籌當週進度,並提供股票相關知識。除了基礎預測模型外,我也負責最後的融合模型。
第二週由於無法透過股市歷史資料很好的預測,又由於四人都沒有解析新聞資料的能力,我便鼓勵大家嘗試看看各種想法,以學習到經驗、知識為首要目標來進行比賽。
工程上的同步我們透過資料同步的方式來完成,沒有程式碼共同編輯的問題發生。

Paragraph image 02 00@2x
PDF FILE INDEX: English => p. 1; Chinese => p. 5 

【日本語版】【2020.05.22 更新】
Profile 00 00@2x

陳廷睿 チンテイエイ Ting-Rui(Ray) Chen

私は2019年7月で国立中央大学情報工学院から卒業しました。専門分野は深層学習(特にデータ駆動型AIを研究しました)。卒論テーマは「クリックストリーム中の人の行為分析」。私たちは使用者のネット活動を取集のサービスを作られました。修士期間は株価予測関する研究もしました。千万規模な資料処理と資料処理時間の加速(3日から3時間に短縮しました)などの経験も修士期間に得ました。

2019年12月に私はPinkoiに入社しました。そして、COVID-19のせいでPinkoiはダウンサイジングを決定し、私は2020年4月からPinkoiをレイオフされていました。 Pinkoiで働いてたの4ヶ月間に、私はデータパイプライン開発のスピードアップのためにコードリポジトリを再構築しました。これプロジェクトは新しいデータパイプラインを構築するときにチームメンバーは注意することが減って、より効率的にデータを取得できます。数ヶ月に更新停止していたの検索欄のオートコンプリートシステムと3年以上更新停止していたの検索欄のブランドサジェストシステムのプロジェクトを再開しました。オートコンプリートシステムを最新のコードスタイルで再構築し、以前のパフォーマンスも維持しました。ブランドサジェストシステムも最新のコードスタイルで完成し、ブランドのカバー率は約8倍上がりました。 


現役職
国立中央大学 情報工学院 資料分析科学実験室 修士
(深層学習やデータ関するエンジニアの職務を探しています)

+886 988555373
[email protected]


Skills

  • Python (PySpark, Keras, PyTorch, flask, sci-kit learn, …etc.)
  • Elasticsearch(Python api, Python DSL api)
  • SQL (MySQL) 
  • Javascript (jQuery, Vue.js)
  • HTML5 
  • Cloud Computing Platform(Heroku, AWS ElasticBeantalk)
  • C/C++ ;


Licenses & Certifications

  • JLPT N2


基本資料

    2017年2月私は資格を得ましたので、予定より1学期早くで大学から卒業しました。続いては国立中央大学情報工学院の研究助手(2017年3月至2019年7月)を赴任しました、同年9月から修士課程も始まりました。2019年7月で学位を取れました。卒論作る時期、私はゼロからサービスを作られました、このサービスはブラウザの拡張機能として、使用者のネット活動を取集し、レポートを提供する。実験終わる時は総勢150人の使用者でした、およそ1000万動作レコード集取しました、卒論はこの資料を処理と分析し作られました。
    卒論実験始めの前に、私は株価予測関する研究をしました。2018年3月至6月はトレンドマイクロ社のチーム対抗のデータコンペティションに参加し、487チーム中7位の成績をとることができました。また、台湾工業技術研究院のビックデータセンターで2カ月の実習を行いました、主に数値回帰予測関する(材料使用量、世界株価など)モデルを開発しました。

    2019年12月に私はPinkoiに入社しました。そして、COVID-19のせいでPinkoiはダウンサイジングを決定し、私は2020年4月からPinkoiをレイオフされていました。 Pinkoiで働いてたの4ヶ月間に、私はデータパイプライン開発のスピードアップのためにコードリポジトリを再構築しました。これプロジェクトは新しいデータパイプラインを構築するときにチームメンバーは注意することが減って、より効率的にデータを取得できます。数ヶ月に更新停止していたの検索欄のオートコンプリートシステムと3年以上更新停止していたの検索欄のブランドサジェストシステムのプロジェクトを再開しました。オートコンプリートシステムを最新のコードスタイルで再構築し、以前のパフォーマンスも維持しました。ブランドサジェストシステムも最新のコードスタイルで完成し、ブランドのカバー率は約8倍上がりました。


職務経歴

Pinkoi.com,2019年 12月 - 2020年 4月

Routine works are maintaining ETL pipeline, responding the data request from other teams(BI, UX ... etc.) 

Key Achievement:

  1. Refactor Code repository and fix up several issues: Make teammate develop more efficiency than before about 10% fast and more readable than before about 50%.
  2. Search-bar autocomplete system: refactored in new data pipeline and make it renew everyday while keeping the system performance. 
  3. Search-bar brand-suggestion system: redesign it by using association rules for cleaning the user behavior and merging the brand list to maximized the recall. Finally, tuned the performance of the brands' coverage from ~1500 up to ~11000 brands. 

国立中央大学,2017年 3月 - 2019年 7月

研究助手 — 2017.02 - 2019.07,教授からの研究任務を執行する、主にデータ収集のプログラムを開発。
授業助手 — 2018.02 - 2019.01
    Statistical Learning、2018.09 - 2019.01、宿題や試験を訂正作業に務めました。
    Computer Organization、2018.02 - 2018.06、宿題や試験を訂正作業に務めました。

工業技術研究院、インターン、2018年 7月 - 2018年 8月

巨量データセンター商業応用分析技術部で商業予測AI応用を開発に勤めてした。

株式会社ワークスアプリケーションズ、インターン、2017 年 7 月 - 2017 年 7 月

国際コーヒーブランド用 ERPシステムの設計と実現するの偽課題に務めました。

国立彰化(チャンフワー)師範(シーファン)大学,2015 年 2 月 - 2017 年 1 月

授業助手 — 2015.02 - 2017.06
                 Object-Oriented-Programming、2015.02 - 2017.06、宿題や試験を訂正作業に務めました。
                 Advanced Programming Design、 2017.02 - 2017.06、宿題や試験を訂正作業に務めました。
卒業プロジェクト — 2015.07 - 2016.06

               「新仕様な校務データ管理システムの入校関する部分の開発」、2015.07 - 2016.06、チームリーダーを務めました、仕事の分配やプロジェクト進度管理関するの仕事をしました、同時にOracleDBとWeb技術を使用しプロジェクトを遂行しました。
               「校務データ管理システムの部活関する部分のデータ移転」、2015.07 - 2016.02、一人プロジェクト、部活関するデータをMySQL DBからOracleDB 8iに移転の解決方法を開発し、並びに元のプログラムの正しい動作を確認する。

学歴

国立中央大学、情報工学院、資料分析科学実験室 - 修士,2017年 9月 - 2019年 7月

この時期は実験室のHPを開発し、実験室のデータベースやサーバーを建設とメンテナンスに務めました。

国立彰化(チャンフワー)師範(シーファン)大学、情報工学部 — 学士,2013年 9月 - 2017年 1月

資格を得ましたので、予定より1学期早く卒業しました。一般的には6月で卒業式を行います。

出版品

Ting-Rui Chen, Hung-Hsuan Chen. Extended Clickstream: an analysis of the missing user behaviors in the Clickstream, 2019.

Nowadays, people often use clickstream to represent the behavior of online users. However, we found that clickstream only represents part of users' browsing behaviors. For instance, clickstream does not include tab switching and browser window switching. We collect these kinds of behaviors and named as "extended clickstream". This thesis builds a service to capture both of clickstream and extended clickstream, also provides an analysis of the differences between above. We use a Multi-Task learning model with GRU components to perform multi-objective predictions of "what kind of website the user will go next time" and "how long the interval of clicks will be" for the time series of clickstreams and extended clickstreams. Our experimental results show that combining clickstream and extended clickstream can improve the prediction performance. In addition, this article finds that the clickstream will record unintended clicks due to the operation mechanism of certain websites. Moreover, we can differentiate the single user from several devices by combining the clickstream and extended clickstream.

Ting-Rui Chen, Cheng-You Lien, Guo-Jhen Bai, Hung-Hsuan Chen. 使用者長時段跨網站瀏覽資料集之蒐集與分析 TANET '18 Taiwan Academic Network Conference, 2018.

This paper introduces a dataset containing the logs of online users’ long-term cross-website visits. Such type of open dataset is rarely-seen because collecting the logs of users’ long-term cross-website visits is difficult. As a result, opening such a dataset may help the researchers conduct advanced researches, such as online user behavior analysis, user demographical information analysis, recommender systems and online advertising system development, etc. We report the following items in this paper. First, we explain the data collecting process. Second, we show the basic statistics of this dataset. Third, we discuss the concerns to release the complete dataset. Specifically, we discuss the trade-offs between “openness” and “privacy” and our current compromising sharing policy. Fourth, we introduce experiments based on this dataset. Finally, we introduce our current plan for expanding this dataset. Keywords: online log, open data, user behavior.

Cheng-You Lien, Guo-Jhen Bai, Ting-Rui Chen, Hung-Hsuan Chen. Predicting User’s Online Shopping Tendency During Shopping Holidays. TAAI '17 Conference on Technologies and Applications of Artificial Intelligence, 2017.

The number of sales during the shopping holidays continues growing in recent years. Thus, many E-Commerce (EC) websites spend much money and effort for marketing before these shopping holidays. However, in this study we found that only part of the Internet users indeed visited the EC-websites more often than usual during the shopping holidays. Thus the increase of the sales probably comes from few individuals. Additionally, we found that users’ tendency to visit the EC websites during the shopping holiday is predictable based on simple supervised classifiers. Thus, an EC website runner can identify the potential visitors and non-visitors beforehand and apply different marketing strategy to different users.

参照


[1]

Projects 01 00@2x

T-Brain Machine Learning Competition 2 Taiwan ETF Price Prediction Competition 7th Place (Team name: NCU_newbie) We took the first place in the first week of the game period. Analyzing the stock price trend in the game period, we found that stock price trend is similar as historical data in the first week, however, the Taiwan stock price trend in the next three weeks goes with global economic news. Therefore, our model cannot well predict the trend. Finally, we got overall 7th place in this competition. Our models are the deep learning models. Each model gets a prediction then ensemble by a simple machine learning model as a final prediction. Our method can learned the relation from the large-scale stock price historical data, but cannot learned relation from news. As a result, we cannot well predict the trend affect by news.

[2]

I managed the progress of the team and provide my knowledge of stock market to team members. I build base learner for prediction and the ensemble learner. In the second week of game period, we could not well predict the trend and we had no idea on parsing news to features. I suggested our team members to try everything. We set the goal to learn experience and knowledge.

Paragraph image 02 00@2x
Powered by CakeResumePowered by CakeResume