數據驅動開發_開發數據驅動的股票市場投資方法

數據驅動開發

Data driven means that your decision are driven by data and not by emotions. This approach can be very useful in stock market investment. Here is a summary of a data driven approach which I have been taking recently

數據驅動意味著您的決定是由數據而非情感驅動的。 這種方法在股票市場投資中非常有用。 這是我最近采用的數據驅動方法的摘要

停止按庫存分析庫存 (Stop analysing stock by stock)

Being a data scientist, the one thing which I do not like about existing stock market tools is that the analysis is done in a very crude way. The analysis has still to be done for each stock symbol. Something like this

作為數據科學家,我不喜歡現有的股票市場工具的一件事就是分析是非常粗略的。 必須對每個股票代號進行分析。 像這樣

Choose a stock, Analyse it, decide on buy/sell

選擇股票,進行分析,決定購買/出售

Go to second stock, Analyse it, decide on buy/sell

轉到第二只股票,進行分析,決定買入/賣出

Go to third stock, Analyse it, decide on buy/sell

轉到第三只股票,進行分析,決定買入/賣出

etc…

等等…

Image for post
Analysing stock by stock — a very cumbersome way
按庫存分析庫存—非常麻煩

This forces you to choose stock in first place. And the way you choose the stock is based on intuition or news you read about the stock. So there is already some bias introduced in the selection process.

這迫使您首先選擇庫存。 選擇股票的方式是基于您對股票的直覺或新聞。 因此,在選擇過程中已經引入了一些偏見。

The approach which I am using is top-down. Take all possible stocks and then analyse all together

我使用的方法是自上而下的。 盤點所有可能的股票,然后一起分析

Image for post
Data driven approach — Analyse all stocks in one go
數據驅動的方法—一口氣分析所有股票

This way I do not have to think of selection of a particular stock in one place. I just take all stock symbols and analyse all together. Shown here is analysing all stock of CAC40 (French Stock Market)

這樣,我不必在一個地方考慮??選擇特定股票。 我只考慮所有股票代碼并一起分析。 此處顯示的是分析CAC40(法國股票市場)的所有庫存

Image for post

What I get is graph of all stocks together.

我得到的是所有股票的圖表。

Image for post
All stocks are shown together
所有股票一起顯示

This saves me immense amount of time. Earlier I used to spent hours to get the visualisation for 40 stocks. Now I can get visualisation for 40 stocks in matter of seconds

這為我節省了大量時間。 早些時候,我曾經花了幾個小時來獲得40只股票的可視化。 現在,我可以在幾秒鐘內獲得40只股票的可視化

儀表板風格在同一視線中呈現多種視覺效果 (Dashboard style multiple visualisations in same sight)

For those who have been in data profession, know the importance of dashboards which gives multiple visualisations to see at the same time. It helps you make better decisions.

對于那些從事數據行業的人來說,了解儀表板的重要性是可以同時看到多個可視化內容的。 它可以幫助您做出更好的決策。

This approach is very suitable for stock analysis, as one has to focus on multiple technical indicators.

這種方法非常適合于庫存分析,因為它必須關注多個技術指標。

Image for post
Multiple visualisation for same stock symbol
同一股票代號的多個可視化

The above is a good example on power of “seeing” multiple visualisations at same time. The moving average shows an uptrend. However the candlestick graph shows loss in momentum. So there might be a downward trend which might be starting, so would be better to stay away from this stock

上面的示例很好地展示了同時“看到”多個可視化效果的能力。 移動平均線顯示上升趨勢。 但是,燭線圖顯示了動量損失。 因此,可能會有開始下降的趨勢,因此最好遠離該庫存

根據各種標準進行排序 (Sorting based on various criterions)

The sorting functionality is key for any data driven approach. So in my approach I have developed sorting based on various criterions such as Trend, Difference with Moving average etc..

排序功能是任何數據驅動方法的關鍵。 因此,在我的方法中,我根據各種標準(例如趨勢,與移動平均線的差異等)開發了排序。

Just by sorting based on Trend High to low, surfaces “safe or less risky” stocks at the top

僅根據趨勢從高到低排序,頂部的“安全或風險較小”的庫存

Image for post
Sorting by Trend
按趨勢排序

As you can see that CAP.PA surfaces to the top as it has been top trending since long time. This can be confirmed by its upward climbing moving average line. Now that is being data driven. Let data tell you the nature of the stock rather than deciding based on any intuitions

如您所見,CAP.PA一直處于頂部趨勢,因為長期以來一直是趨勢。 這可以通過其向上攀升的移動平均線來確認。 現在這是數據驅動的。 讓數據告訴您股票的性質,而不是根據任何直覺來決定

加入我的網站 (Join my website)

If you are interested in my approach , I have it available on my website https://www.nziter.com. Please check out it.

如果您對我的方法感興趣,可以在我的網站https://www.nziter.com上找到 。 請檢查一下。

翻譯自: https://medium.com/swlh/developing-a-data-driven-approach-in-stock-market-investment-104c2b1e49c4

數據驅動開發

本文來自互聯網用戶投稿,該文觀點僅代表作者本人,不代表本站立場。本站僅提供信息存儲空間服務,不擁有所有權,不承擔相關法律責任。
如若轉載,請注明出處:http://www.pswp.cn/news/389465.shtml
繁體地址,請注明出處:http://hk.pswp.cn/news/389465.shtml
英文地址,請注明出處:http://en.pswp.cn/news/389465.shtml

如若內容造成侵權/違法違規/事實不符,請聯系多彩編程網進行投訴反饋email:809451989@qq.com,一經查實,立即刪除!

相關文章

前端之sublime text配置

接下來我們來了解如何調整sublime text的配置,可能很多同學下載sublime text的時候就是把它當成記事本來使用,也就是沒有做任何自定義的配置,做一些自定義的配置可以讓sublime text更適合我們的開發習慣。 那么在利用剛才的命令面板我們怎么打…

python 時間序列預測_使用Python進行動手時間序列預測

python 時間序列預測Time series analysis is the endeavor of extracting meaningful summary and statistical information from data points that are in chronological order. They are widely used in applied science and engineering which involves temporal measureme…

keras框架:目標檢測Faster-RCNN思想及代碼

Faster-RCNN(RPN CNN ROI)概念 Faster RCNN可以分為4個主要內容: Conv layers:作為一種CNN網絡目標檢測方法,Faster RCNN首先使用一組基礎的convrelupooling層提取 image的feature maps。該feature maps被共享用于…

算法偏見是什么_算法可能會使任何人(包括您)有偏見

算法偏見是什么在上一篇文章中,我們展示了當數據將情緒從動作中剝離時會發生什么 (In the last article, we showed what happens when data strip emotions out of an action) In Part 1 of this series, we argued that data can turn anyone into a psychopath, …

大數據筆記-0907

2019獨角獸企業重金招聘Python工程師標準>>> 復習: 1.clear清屏 2.vi vi xxx.log i-->edit esc-->command shift:-->end 輸入 wq 3.cat xxx.log 查看 --------------------------- 1.pwd 查看當前光標所在的path 2.家目錄 /boot swap / 根目錄 起始位置 家…

Tensorflow框架:目標檢測Yolo思想

Yolo-You Only Look Once YOLO算法采用一個單獨的CNN模型實現end-to-end的目標檢測: Resize成448448,圖片分割得到77網格(cell)CNN提取特征和預測:卷積部分負責提取特征。全鏈接部分負責預測:過濾bbox(通過nms&#…

線性回歸非線性回歸_了解線性回歸

線性回歸非線性回歸Let’s say you’re looking to buy a new PC from an online store (and you’re most interested in how much RAM it has) and you see on their first page some PCs with 4GB at $100, then some with 16 GB at $1000. Your budget is $500. So, you es…

樸素貝葉斯和貝葉斯估計_貝葉斯估計收入增長的方法

樸素貝葉斯和貝葉斯估計Note from Towards Data Science’s editors: While we allow independent authors to publish articles in accordance with our rules and guidelines, we do not endorse each author’s contribution. You should not rely on an author’s works wi…

numpy統計分布顯示

import numpy as np from sklearn.datasets import load_iris dataload_iris()petal_lengthnumpy.array(list(len[2]for len in data[data]))#取出花瓣長度數據 print(np.max(petal_length))#花瓣長度最大值 print(np.mean(petal_length))#花瓣長度平均值 print(np.std(petal_l…

python數據結構:進制轉化探索

*********************************第一部分******************************************************************************************************************************************************************************************# 輸入excel的行號,…

Keras框架:人臉檢測-mtcnn思想及代碼

人臉檢測-mtcnn 概念: MTCNN,英文全稱是Multi-task convolutional neural network,中文全稱是多任務卷積神經網絡, 該神經網絡將人臉區域檢測與人臉關鍵點檢測放在了一起。 從工程實踐上,MTCNN是一種檢測速度和準確率…

python中格式化字符串_Python中所有字符串格式化的指南

python中格式化字符串Strings are one of the most essential and used datatypes in programming. It allows the computer to interact and communicate with the world, such as printing instructions or reading input from the user. The ability to manipulate and form…

Javassist實現JDK動態代理

提到JDK動態代理,相信很多人并不陌生。然而,對于動態代理的實現原理,以及如何編碼實現動態代理功能,可能知道的人就比較少了。接下一來,我們就一起來看看JDK動態代理的基本原理,以及如何通過Javassist進行模…

數據圖表可視化_數據可視化如何選擇正確的圖表第1部分

數據圖表可視化According to the World Economic Forum, the world produces 2.5 quintillion bytes of data every day. With so much data, it’s become increasingly difficult to manage and make sense of it all. It would be impossible for any person to wade throug…

Keras框架:實例分割Mask R-CNN算法實現及實現

實例分割 實例分割(instance segmentation)的難點在于: 需要同時檢測出目標的位置并且對目標進行分割,所以這就需要融合目標檢測(框出目標的位置)以及語義分割(對像素進行分類,分割…

機器學習 缺陷檢測_球檢測-體育中的機器學習。

機器學習 缺陷檢測🚩 目標 (🚩Objective) We want to evaluate the quickest way to detect the ball in a sport event in order to develop an Sports AI without spending a million dollars on tech or developers. Quickly we find out that detec…

莫煩Pytorch神經網絡第二章代碼修改

import torch import numpy as np""" Numpy Torch對比課程 """ # #tensor與numpy格式數據相互轉換 # np_data np.arange(6).reshape((2,3)) # print(np_data) # # torch_data torch.from_numpy(np_data) # print(\n,torch_data) # # tensor2ar…

自定義字符類

當 VC不使用MFC,無法使用屬于MFC的CString,為此自定義一個,先暫時使用,后續完善。 頭文件: #pragma once#define MAX_LOADSTRING 100 // 最大字符數class CString {public:char *c_str, cSAr[MAX_LOADSTRING];WCHAR *w…

使用python和javascript進行數據可視化

Any data science or data analytics project can be generally described with the following steps:通常可以通過以下步驟來描述任何數據科學或數據分析項目: Acquiring a business understanding & defining the goal of a project 獲得業務理解并定義項目目…

Android 事件處理

事件就是用戶對圖形的操作,在android手機和平板電腦上,主要包含物理按鍵事件和觸摸屏事件兩類。物理按鍵事件包含:按下、抬起、長按等;觸摸屏事件主要包含按下、抬起、滾動、雙擊等。 在View中提供了onTouchEvent()方法&#xff0…