Scribd
Upload
58 views7 pages

Financial Data Analysis With AI (2-Weeks)

Uploaded by

Krishna Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
58 views7 pages

Financial Data Analysis With AI (2-Weeks)

Uploaded by

Krishna Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 7

2-weeks Online Training

On
Financial Data Analysis with AI, Machine Learning,
Time Series & Algorithm Trading
Duration: Total 30 Hours

Training Highlights:
5+ Hands-on Projects Total 30+ Hours
covered during the training. Live online Instructor-led Training.

Training includes: Certificate of completion


Projects, Study Material, Training Recording. association with Mechanica IIT Madras

TRAINING MODULES (2-weeks)


Modules: TOPICS
Module 1  Financial Analysis Introduction
 Python Programming
Module 2  Working With Numpy
 Data Manipulation – Cleansing – Munging Using Pandas
 Data Analysis – Visualization Using Python
Module 3  Implementation of Stats Methods
 Machine Learning Foundation
 Machine Learning Algorithms & Applications
Module 4  Time Series Fundamentals
 Simple Time Series
 Arima & Sarima – Time Series Forecasting
Module 5  Introduction to Portfolio Allocation Risk Management
 Finance Fundamentals & Strategy
 Better Investment Decisions – Piotroski F-Score
 Quant Finance
TRAINING PROJECTS:

TRAINING PROJECTS

 Facebook Shares Time Series Data with interesting insights.


Module 1 & 2
 EDA, Data Mangling and Visualizing using Microsoft Financial Data.
 Insights & Analysis Daily Percentage Change, Cumulative Daily Returns,
Comparing Daily Returns using Stock Data

 Hypothesis Testing, P Value, Estimate Average Stock Return on Financial Data


Module 3
 Forecasting Google Shares: Regression Analysis & Predictive using on Google
Shares Price

 Car Stock Market Analysis: Analyzing stock data related to car companies like
Module 4
Tesla vs Ford vs GM from Jan 2012 to Jan 2020.
 Stats Model Analysis: Decomposition, Stationarity Testing, Differencing,
Autocorrelation Plots and Interpretation.
 Monthly Production Forecasting: ARIMA and SARIMA monthly Production
Time Series Forecasting.

 Financial Portfolio Allocation and Optimization: Portfolio Values, Statistics,


Module 5
Sharpe Ratio.
 Piotroski F-score: F-Score calculation, how good Piotroski F-score predicts
stock returns, Plotting the Piotroski F-Score.
 Trading Strategy on Financial Data: Implementation of Financial Back testing,
First Trading Algorithm
COURSE CONTENT (2-weeks [30-HOURS])
FINANCIAL ANALYSIS, TIME SERIES AND ALGORITHM TRADING

COURSE CONTENT (30-Hours)

FINACIAL ANALYSIS INTRODUCTION


 What is Data Science
TERM 1:  What is Machine Learning
 Machine Learning vs. Data Science vs. AI
 How information hierarchy can be improved/introduced
 Overview of Analytics for Banking
 Understanding Financial Analysis
 How leading companies are harnessing the power of Data Science with Python?
 Different phases of a typical Financial Analytics projects
 Supervised Learning, Semi-Supervised and Unsupervised Learning
 Regression vs. Classification

PYTHON PROGRAMMING
 Overview of Python- Starting with Python
 Python data types: Primitive
 Core built-in data structures – Lists, Tuples, Dictionaries, Sets
 String, String built-in methods
 Data manipulation tools (Operators, Functions, Packages, control structures,
Loops, arrays etc)
 Loops and Conditional statements (for, while loop)
 Python UDFs – def keywords

TERM 2
WORKING WITH NUMPY
 Numpy Overview
 Properties, Purpose, and Types of ndarray
 Class and Attributes of ndarray Object
 Basic Operations: Concept and Examples
 Accessing Array
 Elements: Indexing, Slicing, Iteration, Indexing with Boolean Arrays
 Shape Manipulation & Broadcasting
 Linear Algebra using numpy
 Stacking and resizing the array

DATA MANIPULATION – CLEANSING – MUNGING USING PANDAS


 Import data from spreadsheets, text files and statistical formats like SPSS.
 Cleansing Data with Python
 Data Manipulation steps (Sorting, filtering, duplicates, merging, appending,
subsetting, derived variables, sampling, Data type conversions, renaming,
formatting etc)
 Scaling and Normalizing data
 Pre-processing and Formatting data
 Feature selection – Correlation etc.. Basic Statistics - Measures of Central
Tendencies and Variance
 Important Python packages for data manipulation.

DATA ANALYSIS – VISUALIZATION USING PYTHON


 Introduction exploratory data analysis
 Descriptive statistics, Frequency Tables and summarization
 Univariate Analysis (Distribution of data & Graphical Analysis)
 Bivariate Analysis (Cross Tabs, Distributions & Relationships, Graphical Analysis)
 Creating Graphs- Bar/pie/line chart/histogram/ boxplot/ scatter/
density/Correlation etc.)
 Introduction to Spatial Analysis
 Sub plotting,

PROJECTS TERM1 & TERM2


 Facebook Shares Time Series Data with interesting insights.
 EDA, Data Mangling and Visualizing using Microsoft Financial Data.
 Insights & Analysis Daily Percentage Change, Cumulative Daily Returns,
Comparing Daily Returns using Stock Data

TERM 3
IMPLEMENTATION OF STATS METHODS
 Basic Statistics - Measures of Central Tendencies and Variance
 Building blocks - Probability Distributions - Normal distribution
 Central Tendency, Standard Deviation
 Quartiles, IQR, Boxplot, Outliers
 Skewness, Kurtosis
 Hypothesis Testing – Anova, t-Test, P Values
 PCA t-Distr. Stochastic Neigh. Emb. (t-SNE)
 Empirical Distribution

MACHINE LEARNING FOUNDATION


 Introduction to Machine Learning & Predictive Modeling
 Types of Business problems - Mapping of Techniques - Regression vs.
classification vs. segmentation vs. Forecasting
 Major Classes of Learning Algorithms -Supervised vs Unsupervised Learning
 Different Phases of Predictive Modeling (Data Pre-processing, Sampling, Model
Building, Validation)
 Overfitting (Bias-Variance Trade off) & Performance Metrics
 Feature engineering & dimension reduction
 Concept of optimization & cost function
 Concept of Cross validation (Bootstrapping, K-Fold validation etc.)

MACHINE LEARNING ALGORITHMS & APPLICATIONS

REGRESSION
 Regression Problem Analysis
 Mathematical modelling of Regression Model
 Gradient Descent Algorithm
 Use cases
 Regression Table
 Model Specification
 L1 & L2 Regularization
 Optimizers
 Polynomial Linear Regression
 Data sources for Linear regression
 Parameters & Hyperparameters
 Cost Function & Cost Optimizer: Gradient Descent Algorithm
 Algorithm Metrics R Squared & Adj. Squared

PROJECTS TERM3
 Hypothesis Testing, P Value, Estimate Average Stock Return on Financial Data
 Forecasting Google Shares: Regression Analysis & Predictive using on Google
Shares Price

TERM 4 TIME SERIES FUNDAMENTALS


 Time Series Dataset
 Collect Trading Data with Pandas Library
 Time Series Vectors and Lags
 Stationarity
 EWMA and Smoothers
 ETS Decomposition
 Time Series Analysis by State Space Methods

SIMPLE TIME SERIES


 Autocorrelation Function
 Compute the ACF, PACF
 White Noise
 Random Walk
 Generate a Random Walk, Get the Drift
 How About Stock Returns?
 Seasonal Adjustment During Tax Season

ARIMA & SARIMA – TIME SERIES FORECASTING


 ARIMA Models for Univariate
 ARIMA Parameter Selection
 ARIMA Residuals
 Manual ARIMA Model Calculation
 Identify ARIMA Model Parameters: General Rules
 ARIMA Forecasts
 SARIMA Forecasting
 Compare AR Model with Random Walk

PROJECTS TERM 4:
 Car Stock Market Analysis: Analyzing stock data related to car companies like
Tesla vs Ford vs GM from Jan 2012 to Jan 2020.
 Stats Model Analysis: Decomposition, Stationarity Testing, Differencing,
Autocorrelation Plots and Interpretation.
 Monthly Production Forecasting: ARIMA and SARIMA monthly Production Time
Series Forecasting.

INTRODUCTION TO PORTFOLIO ALLOCATION RISK MANAGEMENT


TERM 5  How to measure volatility - Volatility Calculation
 Investment, Portfolio Value, Portfolio Statistics
 Shape Ratio
 Ordinary Least-Squares Regression
 Univariate Investment Risk
 Portfolio Investing Factor Investing Forecasting
 Reducing Risk
 Implementation of Back Test Strategy

FINANCE FUNDAMENTALS & STRATEGY


 Portfolio Optimization
 Monte Carlo Simulation
 Functionalize Return and SR operations
 Efficient Frontier
 Creating our Machine Learning Classifiers
 CAPM

BETTER INVESTMENT DECISIONS – PIOTROSKI F-SCORE


 Piotroski F-score Model
 Profitability, Funding, Efficiency Investment Strategy

QUANT FINANCE
 Initialize, Before Trading, & Handle Data
 Context & Order Target Percent
 Order Types & Short Selling
 Schedule Function & Portfolio Rebalancing
 Historical Data
 Closing Positions & Conclusion

PROJECT TERM 5

 Financial Portfolio Allocation and Optimization: Portfolio Values, Statistics,


Sharpe Ratio.
 Piotroski F-score: F-Score calculation, how good Piotroski F-score predicts stock
returns, Plotting the Petroski F-Score.
 Trading Strategy on Financial Data: Implementation of Financial Back testing,
First Trading Algorithm
Training Highlights

 30+ Hours live online Instructor-led Hands-on based learning with Projects.
 Training includes: Soft copy of Training material, Training PPT's, Project code & Training
Recording.
 Training certificate of completion will be provided to each Attendee.

Who can attend?


 Training is best suitable for Engineering college faculty, Research scholar, Student & Working IT
Professional.

EduxLabs Teams
(Esoir Business Solutions Gurugram)
M: +91-7053133032 | 8318635606
Email [email protected]| www.eduxlabs.com

You might also like