楊淨
    • Create new note
    • Create a note from template
      • Sharing URL Link copied
      • /edit
      • View mode
        • Edit mode
        • View mode
        • Book mode
        • Slide mode
        Edit mode View mode Book mode Slide mode
      • Customize slides
      • Note Permission
      • Read
        • Only me
        • Signed-in users
        • Everyone
        Only me Signed-in users Everyone
      • Write
        • Only me
        • Signed-in users
        • Everyone
        Only me Signed-in users Everyone
      • Engagement control Commenting, Suggest edit, Emoji Reply
    • Invite by email
      Invitee

      This note has no invitees

    • Publish Note

      Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note

      Your note will be visible on your profile and discoverable by anyone.
      Your note is now live.
      This note is visible on your profile and discoverable online.
      Everyone on the web can find and read all notes of this public team.
      See published notes
      Unpublish note
      Please check the box to agree to the Community Guidelines.
      View profile
    • Commenting
      Permission
      Disabled Forbidden Owners Signed-in users Everyone
    • Enable
    • Permission
      • Forbidden
      • Owners
      • Signed-in users
      • Everyone
    • Suggest edit
      Permission
      Disabled Forbidden Owners Signed-in users Everyone
    • Enable
    • Permission
      • Forbidden
      • Owners
      • Signed-in users
    • Emoji Reply
    • Enable
    • Versions and GitHub Sync
    • Note settings
    • Note Insights
    • Engagement control
    • Transfer ownership
    • Delete this note
    • Save as template
    • Insert from template
    • Import from
      • Dropbox
      • Google Drive
      • Gist
      • Clipboard
    • Export to
      • Dropbox
      • Google Drive
      • Gist
    • Download
      • Markdown
      • HTML
      • Raw HTML
Menu Note settings Versions and GitHub Sync Note Insights Sharing URL Create Help
Create Create new note Create a note from template
Menu
Options
Engagement control Transfer ownership Delete this note
Import from
Dropbox Google Drive Gist Clipboard
Export to
Dropbox Google Drive Gist
Download
Markdown HTML Raw HTML
Back
Sharing URL Link copied
/edit
View mode
  • Edit mode
  • View mode
  • Book mode
  • Slide mode
Edit mode View mode Book mode Slide mode
Customize slides
Note Permission
Read
Only me
  • Only me
  • Signed-in users
  • Everyone
Only me Signed-in users Everyone
Write
Only me
  • Only me
  • Signed-in users
  • Everyone
Only me Signed-in users Everyone
Engagement control Commenting, Suggest edit, Emoji Reply
  • Invite by email
    Invitee

    This note has no invitees

  • Publish Note

    Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note

    Your note will be visible on your profile and discoverable by anyone.
    Your note is now live.
    This note is visible on your profile and discoverable online.
    Everyone on the web can find and read all notes of this public team.
    See published notes
    Unpublish note
    Please check the box to agree to the Community Guidelines.
    View profile
    Engagement control
    Commenting
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    • Everyone
    Suggest edit
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    Emoji Reply
    Enable
    Import from Dropbox Google Drive Gist Clipboard
       owned this note    owned this note      
    Published Linked with GitHub
    Subscribed
    • Any changes
      Be notified of any changes
    • Mention me
      Be notified of mention me
    • Unsubscribe
    Subscribe
    # 資產配置 計畫書 ### 工作分配 | Member | duty | | ------ | -------- | | 楊+韓 | 背景,研究方法| | 白+謝+tina+OIFO | survey | ### 目標 實驗?系統? * 用機器學習的方法,實驗能否提供好的資產配置建議一半一半(ML DL; 傳統計量),驗證其實驗結果 * 之後可以建立出一整套資產配置推薦系統驗證 ### 要survey東西 **盡量是論文,太多網路資料可能不嚴謹** * 為什麼資產配置很重要,做資產配置有哪些幫助與優點? <font color="#00f">(白崇佑)</font> * 目前資產配置的方式有哪些 & 比較 <font color="#00f">(何元斌)</font> * 傳統 (ex. capm, black litterman etc) * machine learning based * 目前的方式有什麼不足的地方(?) <font color="#00f">(謝傑勝)</font> * 傳統方式:過去傳統方法有不太好的地方(ex: 3月那波,傳統計量模型也做的不好,然後再接到機器學習的優點與優勢) * ML based:為什麼要混ML與傳統計量模型的原因,為何不只做全RL(RL的優點與缺點) * 一般資產配置績效對照用 Benchmark 的選擇 <font color="#00f">(謝傑勝)</font> * ETF資產配置相關研究 <font color="#00f">(tina)</font> * 為什麼要多市場 * 使用的資料(總經指標,匯率,利率(交易etf要看)) * 挑選的ETF * 評估資產配置的方法(績效)<font color="#00f">(白崇佑)</font> ### 背景 傳統主動型投資近期被大眾認為,績效並沒有被動型投資的好,所以近年來,robert adviser越來越熱門,正在發展中,尚未完善,但仍有一些資產過於集中的問題等等。 我們想以機器學習的方法去探討他,目前有很多資產配置的方法,而一般傳統的方法偏向xxx,xxx,想透過機器學習方法,應用在資產配置上,實驗能否有更好的配置方法。 ### 研究方法 * 資料來源: * 台股ETF * 國外ETF資料(S&P500..等等) * 大額交易人、三大法人 * 台灣各項指數 * 各國大盤指數 * gdp? * 各國匯率 * 基本利率 * 傳統總經指標 * 模型: 一半一半(機器學習,深度學習,傳統計量) * 傳統計量 多種比較 最後再選1-多種 * 輸入? * Benchmark選擇 * buy and hold * 對照指數來比較 * 流程: * 透過網路爬蟲蒐集相關資訊 * 資料前處理(標籤、相關資料配對) * 建立資產配置推薦模型 * 驗證模型推薦組合的績效(sharpe ratio, beta, sigma) ### 檢查點 * 期中(半年): * 資料蒐集及資料庫建立,並能以api輕鬆取得資料 (show 資料庫 and api 表示有做事) * 初步模型績效結果(初步模型架構仍須調整) * 資料前處理eda (初步指數等等報告) * 期末 : * 績效評估 * 追蹤指數(打敗大盤or某檔etf ex vix,0050) * 不同模型比較、不同資料建立比較 * 生出一篇論文(可當碩論) ### 可能遭遇困難 * 資料蒐集困難(缺失、不足、爬蟲被BAN等問題) * 資料正確性問題 * 績效不佳(未達預期) * 模型訓練困難 ### 甘特圖: 1 蒐集資料 2 蒐集資料 3 模型建立 4 模型建立 5 模型建立 6 模型建立 7 實驗 8 實驗 9 實驗 10 實驗 11 實驗 12 檢討 ### 文獻蒐集 | 重點摘要 | 作者(發表年)、完整名稱(可能包含頁碼)| 網址| | ------- |---- | --- | | 基礎商院教科書,講解一般投資組合、基礎資產配置理論等等 | Elton, Edwin J., Gruber, Martin J., Brown, Stephen J., Goetzmann, William N, *Modern Portfolio Theory and Investment Analysis, 9th* | 原文書 已po在雲端 (計畫/ref) | | 分布資產分配在Equities , Fixed income , global real estate and cash | ETF portfolio 參考<br />State Street Strategic Asset Allocation ETF Portfolios | https://www.ssga.com/library-content/pdfs/etf/us/strategic-asset-allocation-etf-portfolio-factsheet-q4-19.pdf | | 選擇ETF好處是,可以選不同產業類別,購買其相關的ETF,另外也簡單介紹如何選ETF,(ex. Sector ETFs , International ETFs, Commodity ETFs) | 說明簡單的「全ETF投資組合」 | https://www.investopedia.com/articles/exchangetradedfunds/11/building-an-etf-portfolio.asp | | 多市場、多產業、相關性低,低風險組合 | ETF資產配置科普 | https://www.fsc.gov.tw/fckdowndoc?file=/01-1-05-16-專題一-從ETF談資產配置.pdf&flag=doc | | 結合Inflation rate的總經因素來建立M-GARCH,提供好的風險收益投資組合 | 總經對資產配置影響 <br />T.J. Flavin , M.R. Wickens ,*Macroeconomic Influences on Optimal Asset Allocation* , 2001 | http://repec.maynoothuniversity.ie/mayecw-files/N1080301.pdf | | 沒啥重點,主要是說,全球性的資產分配(不用仔細看) | Magnus Dahlquist , Campbell R. Harvey, *Global Tactical Asset Allocation* , 2001 | https://papers.ssrn.com/sol3/papers.cfm?abstract_id=795376 | | 資產分配模型介紹(不用看,直接放就好,但是我找不到他pdf 可以跳過這個qq) | Asset allocation models<br />[這個看不了qq 可能可以不用管這篇抱歉] | [Journal of Securities Operations & Custody](https://www.ingentaconnect.com/content/hsp/jsoc;jsessionid=778b8o8lebc3a.x-ic-live-01), Volume 6 / Number 1 / Autumn/Fall 2013, | | DL優化投資組合,但沒提到資產分配 | Min-Yuh Day; Jian-Ting Lin; Yuan-Chih Chen , *Artificial Intelligence for Conversational Robo-Advisor* , *2018 IEEE / ACM International Conference on ASONAM* | https://ieeexplore.ieee.org/abstract/document/8508269 | | DL做全球資產配置 (感覺也是放著就好不用看) | Chakravorty, Gaurav and Awasthi, Ankit and Da Silva, Brandon, *Deep Learning for Global Tactical Asset Allocation , 2018* | https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3242432 | | 偏向經濟及財工,在講國際的資產配置轉移等等,可以簡單參考(引用次數多) | Andrew Ang, Geert Bekaert , *International Asset Allocation With Regime Shifts* ,*The Review of Financial Studies, Volume 15, Issue 4, July 2002* | https://academic.oup.com/rfs/article/15/4/1137/1568247?login=true | | 用DL來做投資組合,交易標的是ETF,最佳化投資組合的sharpe ratio | Zihao Zhang, Stefan Zohren, Stephen Roberts , *Deep Learning for Portfolio Optimisation* , 2020 | https://arxiv.org/pdf/2005.13665.pdf | | 可以選不同的類別的來參考,目前想法是選產業別+外匯(美金、RMB) | 台灣ETF種類參考 | https://www.jihsun.com.tw/md/event/jsun_school/ETF_stock10.html | |||| |改進black litterman之資產配置,對black litterman之輸入資產的分布做各種不同假設,使用不同的風險衡量公式|Rosella Giacometti,Marida Bertocchi,Svetlozar T.Rache<br />Stable distributions in the Black–Litterman approach to asset allocation|https://www.tandfonline.com/doi/abs/10.1080/14697680701442731| |基於black litterman之資產配置,將black litterman結合Momentum,應用在台灣股市市場|hyh-Weir TzangChun-Ping ChangChih-Hsing HungYung-Shun Tsai<br />Black-Litterman Model and Momentum Strategy: Evidence of Taiwan Top 50 ETF|https://link.springer.com/chapter/10.1007/978-3-030-50399-4_47| |著重探討risk free asset對CAPM模型之影響|Ippei Suzuki and Takashi Shinzato<br />Macroscopic theorem of the portfolio optimization problem with a risk-free asset|https://arxiv.org/pdf/1906.08892.pdf| |探討CAPM模型在台灣股市之應用,CAPM模型之參數選擇,探討各產業股市之特性|邱世淦<br />以資本資產定價模型為基礎驗證台灣上市公司個股期望報酬與實際報酬之關係|https://ndltd.ncl.edu.tw/cgi-bin/gs32/gsweb.cgi?o=dnclcdr&s=id=%22101NSYS5121090%22.&searchmode=basic| | 基於CAPM之資產配置模型,可根據使用者判斷調整各項 資產之權重(black litterman) |Fischer Black and Robert Litterman<br />Global Portfolio Optimization|https://www.jstor.org/stable/pdf/4479577.pdf | |use stochastic control approach to achieve Portfolio Optimization| Nicole Bauerle and Sascha Desmettre<br />Portfolio Optimization in Fractional and Rough Heston Models|https://epubs.siam.org/doi/pdf/10.1137/18M1217243|ao Zhang, Stefan Zohren, Stephen Roberts , Deep Learning for Portfolio Optimisation , 2020 https://arxiv.org/pdf/2005.13665.pdf |基於機器學習之資產配置,基於mean-variance optimization的方法,再結合regression model|Sarah Perrin and Thierry Roncalli<br />Machine Learning Optimization Algorithms & Portfolio Allocation|https://arxiv.org/pdf/1909.10233.pdf| |基於mean variance之強化學習資產配置模型|Haoran Wang Xun Yu Zhou<br />Continuous‐time mean–variance portfolio selection: A reinforcement learning framework|https://onlinelibrary.wiley.com/doi/full/10.1111/mafi.12281| | 基於深度學習之資產配置,使用Stacked autoencoders衡量個股與全體股市之相似性|J. B.Heaton & N. G.Polson & J. H.Witte<br />Deep learning for finance: deep portfolios|https://onlinelibrary.wiley.com/doi/pdf/10.1002/asmb.2209| |基於強化學習之資產配置,使用Direct Policy Gradient Algorithm直接更新model,架構有兩個network,分別計算price、asset correlation,著重於交易成本及風險控管|Yifan Zhang, Peilin Zhao, Bin Li, Junzhou Huang,Qingyao Wu and Mingkui Tan <br /> Cost-Sensitive Portfolio Selection via Deep Reinforcement Learning|https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9031418| |資產配置定義:透過將資金投資到不同類型的資產類別上,達成期望的風險與報酬配置。目標:犧牲少部分報酬來減少不確定性(減少波動) 原理:兩個資產間走勢「負相關」或「無相關」|說明資產配置的定義,目標與原理|https://rich01.com/how-asset-allocation-1/| |用圖表說明risk-return tradeoff,解釋投資組合與risk tolerance的關係|如何達到資產配置最佳化|https://www.investopedia.com/managing-wealth/achieve-optimal-asset-allocation/| |to introduce an original computational framework to model portfolio allocation strategies; providing a new portfolio score, based on the aforementioned framework and concepts|Modeling asset allocation strategies and a new portfolio performance score|https://arxiv.org/pdf/2012.05088.pdf Apostolos Chalkis and Ioannis Z. Emiris. Modeling asset allocation strategies and a new portfolio performance score. arXiv:2012.05088v2 [q-fin.PM] 10 Dec 2020| |main feature that distinguishes our methodology from conventional performance evaluation methods is that <font color="#00f">it tackles the performance at the decision-making level: the portfolio weights.</font>(找不到投影片)|Performance evaluation of constrained portfolios| I. Pouchkarev. Performance evaluation of constrained portfolios. PhD thesis, Erasmus Research Institute of Management, The Netherlands, 2005.| |說明資產配置的重要性。explain the impact of the long-term assetallocation policy mix relative to the impact of active performance from timing, security selection, and fees|The Importance of Asset Allocation|https://www.researchgate.net/publication/256006024_The_Importance_of_Asset_Allocation Roger G Ibbotson. The Importance of Asset Allocation. Article in Financial Analysts Journal · August 2009| |Conclusion有提到RL的優缺點|Zhipeng Liang, Hao Chen, Junhao Zhu, Kangkang Jiang, Yanran Li. "Adversarial Deep Reinforcement Learning in Portfolio Management." arXiv preprint arXiv:1808.09940 (2018).|https://arxiv.org/pdf/1808.09940.pdf| |傳統CAPM的優缺點|Kristina Zucchi. "CAPM Model: Advantages and Disadvantages." Investopedia (2019).|https://www.investopedia.com/articles/investing/021015/advantages-and-disadvantages-capm-model.asp| |根據資產類別選擇適合的Benchmark,例如:投資組合有許多large-cap US stocks則可用S&P500當benchmark|Benchmark|https://corporatefinanceinstitute.com/resources/knowledge/trading-investing/benchmark/| |介紹CAPM及討論現代投資組合理論研究中的困難|Xingang Wang. "Theoretical Analysis of Financial Portfolio Model." iBusiness 05(03):69-73 (2013).|https://www.researchgate.net/publication/276494475_Theoretical_Analysis_of_Financial_Portfolio_Model| |機器學習投資組合配置有較大的回報|Michael Pinelis, David Ruppert. "Machine Learning Portfolio Allocation." arXiv preprint arXiv:2003.00656 (2020).|https://arxiv.org/pdf/2003.00656.pdf| |多位學者對於計量經濟學與機器學習混和的看法|Eric Zheng et al. "When Econometrics Meets Machine Learning." Data and Information Management, 1(2): 75–83 (2017).|https://content.sciendo.com/view/journals/dim/1/2/article-p75.xml?language=en&tab_body=fullHtml-79543| ## 檢討 計畫tips ### 背景 - 創新性:和別的企劃差在哪裡,其他人做過什麼(所有的文獻) - 鋪陳至為什麼要做這個:由於xxx,xxx,所以xxx,不能一下子直接跳 - 參考文章時應該整段看,也可以找一篇引用數中間的整段複製,然後不要放在ref ### 研究方法 - 闡明研究目標、舉例相關研究、近期發展現況 - 模型詳細:參考別人的計畫,應該要寫多詳細,才代表我們真的有survey - 定義研究方法、需要詳細說明研究方法 - 一開始討論大綱就要稍微訂出甘特圖 ### survey - survey的時候,可以寫個article,有個概念知道要放什麼,或是要寫什麼,比較好知道要survey啥

    Import from clipboard

    Paste your markdown or webpage here...

    Advanced permission required

    Your current role can only read. Ask the system administrator to acquire write and comment permission.

    This team is disabled

    Sorry, this team is disabled. You can't edit this note.

    This note is locked

    Sorry, only owner can edit this note.

    Reach the limit

    Sorry, you've reached the max length this note can be.
    Please reduce the content or divide it to more notes, thank you!

    Import from Gist

    Import from Snippet

    or

    Export to Snippet

    Are you sure?

    Do you really want to delete this note?
    All users will lose their connection.

    Create a note from template

    Create a note from template

    Oops...
    This template has been removed or transferred.
    Upgrade
    All
    • All
    • Team
    No template.

    Create a template

    Upgrade

    Delete template

    Do you really want to delete this template?
    Turn this template into a regular note and keep its content, versions, and comments.

    This page need refresh

    You have an incompatible client version.
    Refresh to update.
    New version available!
    See releases notes here
    Refresh to enjoy new features.
    Your user state has changed.
    Refresh to load new user state.

    Sign in

    Forgot password

    or

    By clicking below, you agree to our terms of service.

    Sign in via Facebook Sign in via Twitter Sign in via GitHub Sign in via Dropbox Sign in with Wallet
    Wallet ( )
    Connect another wallet

    New to HackMD? Sign up

    Help

    • English
    • 中文
    • Français
    • Deutsch
    • 日本語
    • Español
    • Català
    • Ελληνικά
    • Português
    • italiano
    • Türkçe
    • Русский
    • Nederlands
    • hrvatski jezik
    • język polski
    • Українська
    • हिन्दी
    • svenska
    • Esperanto
    • dansk

    Documents

    Help & Tutorial

    How to use Book mode

    Slide Example

    API Docs

    Edit in VSCode

    Install browser extension

    Contacts

    Feedback

    Discord

    Send us email

    Resources

    Releases

    Pricing

    Blog

    Policy

    Terms

    Privacy

    Cheatsheet

    Syntax Example Reference
    # Header Header 基本排版
    - Unordered List
    • Unordered List
    1. Ordered List
    1. Ordered List
    - [ ] Todo List
    • Todo List
    > Blockquote
    Blockquote
    **Bold font** Bold font
    *Italics font* Italics font
    ~~Strikethrough~~ Strikethrough
    19^th^ 19th
    H~2~O H2O
    ++Inserted text++ Inserted text
    ==Marked text== Marked text
    [link text](https:// "title") Link
    ![image alt](https:// "title") Image
    `Code` Code 在筆記中貼入程式碼
    ```javascript
    var i = 0;
    ```
    var i = 0;
    :smile: :smile: Emoji list
    {%youtube youtube_id %} Externals
    $L^aT_eX$ LaTeX
    :::info
    This is a alert area.
    :::

    This is a alert area.

    Versions and GitHub Sync
    Get Full History Access

    • Edit version name
    • Delete

    revision author avatar     named on  

    More Less

    Note content is identical to the latest version.
    Compare
      Choose a version
      No search result
      Version not found
    Sign in to link this note to GitHub
    Learn more
    This note is not linked with GitHub
     

    Feedback

    Submission failed, please try again

    Thanks for your support.

    On a scale of 0-10, how likely is it that you would recommend HackMD to your friends, family or business associates?

    Please give us some advice and help us improve HackMD.

     

    Thanks for your feedback

    Remove version name

    Do you want to remove this version name and description?

    Transfer ownership

    Transfer to
      Warning: is a public team. If you transfer note to this team, everyone on the web can find and read this note.

        Link with GitHub

        Please authorize HackMD on GitHub
        • Please sign in to GitHub and install the HackMD app on your GitHub repo.
        • HackMD links with GitHub through a GitHub App. You can choose which repo to install our App.
        Learn more  Sign in to GitHub

        Push the note to GitHub Push to GitHub Pull a file from GitHub

          Authorize again
         

        Choose which file to push to

        Select repo
        Refresh Authorize more repos
        Select branch
        Select file
        Select branch
        Choose version(s) to push
        • Save a new version and push
        • Choose from existing versions
        Include title and tags
        Available push count

        Pull from GitHub

         
        File from GitHub
        File from HackMD

        GitHub Link Settings

        File linked

        Linked by
        File path
        Last synced branch
        Available push count

        Danger Zone

        Unlink
        You will no longer receive notification when GitHub file changes after unlink.

        Syncing

        Push failed

        Push successfully