Description

Say hello to Sentiment Based Investment Analysis done right. Leverage the power of Natural Language Processing (NLP) techniques to exploit Sentiment for Financial Analysis / Investment Analysis (with Python), while rigorously validating your hypothesis.

Explore the power of text data for conducting financial analysis / investment analysis rigorously, using hypothesis driven approaches that are rigorously grounded in the academic and practitioner literature. All while leveraging the power of Python.

Discover what Natural Language Processing (NLP) is, and how it’s applied in Finance.

Master the systematic 5 Step Process for Sentiment Analysis while working with a large sample of messy real world data obtained from credible sources, for free.

5 SECTIONS TO MASTERY (plus, all future updates included).

Introduction to Natural Language Processing & Sentiment Analysis in Finance

   Gain an overview of what Natural Language Processing (NLP) is in the context of Finance.
   Discover the wealth of applications of Natural Language Processing (NLP) techniques in Finance, both in the academic and practitioner literature – for Context, Compliance, and Quantitative Analysis (aka, at least in principle, financial analysis / investment analysis).
   Explore what Sentiment Analysis is, and learn about the 5 Step Process to conducting sentiment analysis in a rigorous and statistically robust manner.

Hypothesis Design & Exploratory Data Analysis

   Learn how you can formally express your investment ideas / investing thesis by transforming them into testable hypotheses that are short, ultra-specific, and measurable.
   Explore the wealth of data sources available, and how you can let your hypothesis drive the choice of data.
   Avoid the GIGO trap. See what it takes to really know your data with exploratory data analysis techniques designed to hold you in good stead when you get around to conducting sentiment based financial analysis / investment analysis.

Estimating Firm Level Sentiment

   Become a pro at quantifying sentiment / emotions of companies so you can use them for financial analysis / investment analysis.
   Apply lexicon / dictionary based approaches to estimating sentiment while critically evaluating alternative approaches (e.g. using “machine learning” based approaches and why they can’t be applied in some cases).
   Explore computations of sentiment “manually”, leveraging the power of built in methods inside Python’s NLTK framework.

Estimating Sentiment Portfolio Returns

   Link / merge your firm level sentiment estimates with stock price and returns data to evaluate relationships between sentiment and returns (reap the rewards of your hard work by finally conducting sentiment analysis!).
   Discover how to merge daily data with annual data, while using the “ffill” method built into Python to maintain a daily database with ease.
   Estimate quintile sorted sentiment portfolio returns and prep the data for the final push.

Sentiment / Natural Language Processing (NLP) based Investment Analysis

   Avoid guesswork by leveraging the power of statistics to rigorously test and validate your hypothesis in a robust manner.
   Gain a solid insight into why the statistics makes sense, including why we use a specific statistical test
   Explore what to do when things don’t quite go the way you expected them to. And finally learn whether sentiment actually matters.

DESIGNED FOR DISTINCTION

We’ve used the same tried and tested, proven to work teaching techniques that’ve helped our clients ace their exams and become chartered certified accountants, get hired by the most renowned investment banks in the world, and indeed, manage their own portfolios.

Here’s how we’ll help you master financial analysis and sentiment analysis, and turn you into a PRO at Financial Analysis / Investment Analysis with Natural Language Processing (NLP) on Python:

A Solid Foundation

You’ll gain a solid foundation of the core fundamentals that drive the entire financial analysis / investment analysis process. These fundamentals are the essence of financial analysis and sentiment analysis done right.

Code-along Walkthroughs

Forget about watching videos where all the code’s written out. We’ll start from a blank Jupyter Notebook. And code everything from scratch, one line at a time. That way you’ll literally see how we conduct rigorous financial analysis / investment analysis using Natural Language Processing (NLP) / sentiment as the core basis, one step at a time.

Loads of Practice Questions

Apply what you learn immediately with 100+ practice questions, all with impeccably detailed solutions. Plus, assignments that take you outside your comfort zone.

Proofs & Resources

Mathematical proofs for the mathematically curious, workable .ipynb and .py Python code – all included.
Who this course is for:

   Serious investors wanting to work with robust techniques that are rigorously grounded in academic and practitioner literature.
   Analysts, and aspiring Investment Bankers wanting to future proof themselves and their core skillsets by learning how to leverage the power of text data.
   Finance Managers keen on applying conceptual techniques including Natural Language Processing (NLP) and Sentiment Analysis in Finance / Investment contexts.
   Ivy League / Russell Group University students looking to future proof themselves, increase their competitive advantage, and enhance their skills.

Requirements

   Coding knowledge is REQUIRED. You don’t need to be an ‘expert’ in Python, but you DO need to know how to code.
   At a minimum, we assume you know what lists, dictionaries, and tuples are; and you know the difference between strings, integers, and floats.
   Knowledge of Core Investment Analysis concepts is REQUIRED.
   At a minimum, we assume you know how to estimate stock returns, and quantify risk (e.g. standard deviation).
   See our sister course on Investment Analysis & Portfolio Management (with Python) if you don’t know these core concepts yet.
   Knowledge of basic statistical analysis is useful but NOT essential.
   You’ll need a development environment (e.g. Jupyter Notebooks, Text Editors)
   We work with Jupyter Notebooks in the course, but .py versions of all code is available for download.

Last Updated 11/2020