Last updated 5/2021
MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHz
Language: English | Size: 2.12 GB | Duration: 3h 13m
Learn to stop your Algorithmic Trading System when specific Macroeconomic Events are expected
What you'll learn
Web Text scrapping in R
Learn how to read Macroeconomic news in R
Do Text Sentiment analysis
Setup Automated Decision Support Loop
Automate R scripts
Use Version control for your R project
Writing R functions
Perform data (string) manipulations
Setup Twitter Developer account and read Tweets into Decision Support System
Requirements
You should have a background knowledge on Trading and it's pitfals
You want to learn Data Science using Trading
PC Windows (min 4CPU 8Gb RAM). This machine should be left ON continuously for several weeks
MQL4 and R basic level
Best with 1, 2, 3, 4 courses of Lazy Trading Series
Twitter account
Description
About this Course: Read news and Sentiment AnalysisThe fifth*part of this series will give you the ability to automatically read Forex Calendar for any specific event like US Non-Farm Payroll or when President Trump is going to have a speech. This will provide an ability to consider these events in your trading strategies in a simplest form of disabling the trading robots.Additional research of this course will be about correlation of Asset's Text data Sentiment to the Asset's price in the future. This research will be conducted on two trading ideas*:Sentiment difference of News Headers in the US, Canada, GB and it's their currency Pairs. Sentiment of Twitter data relevant to Tesla Stock pricesAs usual provided methods and ideas will help us to practice computer and data science skills:Webscrap news and analyse their sentiment for tradingSetting up Version Control in our ProjectsKnow how to automate our R codeText Sentiment analysis using basic Sentiment Analysis Polarity Scoring and NRC Sentiment Dictionary (8 emotions)Performing descriptive analysis of the Sentiment Polarity Scoring of the News HeadersGetting Twitter data into RDeep regression learning to correlate Sentiment scores to the objective variable[performed in h2o deep learning environment]*There is*absolutely*no guarantee*that*proposed methods will work!!!About the Lazy Trading Courses:This series of courses is designed to*to*combine fascinating experience of*Algorithmic Trading*and at the same time to*learn*Computer*and*Data Science! Particular focus is made on building foundation of*Decision Support System*that can help to automate a lot of boring processes related to Trading.This project is*containing several short courses*focused to help you managing your Automated Trading Systems:Set up your Home Trading EnvironmentSet up your Trading Strategy RobotSet up your automated*Trading JournalStatistical Automated Trading ControlReading News and Sentiment AnalysisUsing Artificial Intelligence to detect market statusBuilding an*AI trading systemUpdate:*dedicated R package 'lazytrade' was created to facilitate code sharing among different coursesIMPORTANT:*All courses will be short focusing to one specific topic with very short*theoretical explanations. These courses will help*to focus on developing*strategies by automating*boring but important processes for a trader.Best possible way to take the courses as a series is to reproduce all methods by re-creating automated trading system on PC WindowsWhat will you learn apart of trading:While completing these*courses you will learn much more rather than just trading by using provided examples:Learn and practice to use Decision Support SystemBe organized and systematic using Version Control and Automated Statistical AnalysisLearn using R to read, manipulate data and perform Machine Learning including Deep LearningLearn and practice*Data VisualizationLearn sentiment analysis and web scrappingLearn Shiny to deploy any data project in hoursGet productivity hacksLearn to automate your tasks*and scheduling themGet expandable examples of MQL4 and R codeWhat these courses are not:These courses will not teach and explain specific programming concepts in detailsThese courses are not meant to teach basics of Data Science or TradingThere is no guarantee on*bug free programmingDisclaimer:Trading is a risk. This course must not be intended as a financial advice or service. Past results are not guaranteed for the future.
Overview
Section 1: Introduction
Lecture 1 Specific Goals for this Course
Lecture 2 Course Maintenance
Lecture 3 Disclaimer
Section 2: Quick Wins - Examples of how to gather publicly available information
Lecture 4 Section goals
Lecture 5 Video Lecture- news headers and their sentiment
Lecture 6 Code to read news headers
Lecture 7 Read tables from the website Yahoo Finance
Lecture 8 Code to read a tweet about specific topic
Section 3: Web scrapping. Basic Principles
Lecture 9 Goals of this Section
Lecture 10 How to get the code?
Lecture 11 R package 'lazytrade'
Lecture 12 Script to gather info from FxFactory P1
Lecture 13 Install Selector Gadget
Lecture 14 Script to gather info from FxFactory P2
Lecture 15 Reading news on the Schedule (automate it!)
Section 4: Some more data manipulation - Date and Time format
Lecture 16 Goals of this Section - Date and Time basics
Lecture 17 Combine Date and Time columns
Lecture 18 What is really date and time for computers?
Lecture 19 How to calculate number of seconds until year 3000?
Section 5: Reading News and Derive Country Sentiment
Lecture 20 What is Sentiment analysis? Polarity Scoring
Lecture 21 Any good News? Idea of the Forex Social Research!
Lecture 22 Code review: News Sentiment for Decision Support System
Lecture 23 FALCON_S: Put it into production
Lecture 24 FALCON_S: week by week
Lecture 25 FALCON_S: Analyzing Sentiment & increasing threshold
Lecture 26 FALCON_S: Achieved Results
Section 6: Let's get Twitter data!
Lecture 27 Setup Developer Account in Twitter
Lecture 28 Create an App in twitter developer
Lecture 29 Getting code for this section
Lecture 30 Encrypt Tokens in R Script
Lecture 31 Getting twitter data into R
Section 7: Extract Knowledge from Text: Searching and manipulating relevant Twitter content
Lecture 32 Knowledge from Text
Lecture 33 Searching tweets by term methods
Lecture 34 Manipulate and visualize the tweeter content
Lecture 35 More deep Sentiment Analysis of text
Section 8: Predict future price change based on sentiment pattern
Lecture 36 Correlating Sentiment Pattern to price change
Lecture 37 Script to collect sentiment score and price data
Lecture 38 Script to train the deep learning model
Lecture 39 Script to test the deep learning model
Lecture 40 Script to predict price change using model and sentiment scores
Section 9: Analyse results of the Twitter Sentiment Predictive Model
Lecture 41 Goal of this Section
Lecture 42 Reading multiple files from folder
Lecture 43 Visualize the results of predicted price stock
Lecture 44 Evaluate the strategy after 2 month (practice)
Lecture 45 Evaluate the strategy after 2 month (solution)
Lecture 46 Summary Results of the Predicting TeslaMotor price change chapter after 4 Month!
Section 10: Conclusion for Part 5
Lecture 47 Summary of this course
Lecture 48 Your special *BONUS*
Anyone who want to be more productive,Anyone who want to learn Data Science,Anyone who want to try Algorithmic Trading but have little time,Anyone interested in Web Scrapping and Text Analytics
Homepage
Recommend Download Link Hight Speed | Please Say Thanks Keep Topic Live
Links are Interchangeable - No Password - Single Extraction
