Home

Video

Default view
Title
Name
Description
URL
Date
Views
Rating
Dimitri Bianco
After discussing on the podcast about building a personal brand someone asked the question, "why lie" if we know it is bad for our brand? Well to get friends hired. Unfortunately these individuals help enough people to stay in the industry. A lot of favors go around that really shouldn't. In this video I even give a real world example of this hiring process where unqualified people are paid large sums of money and end up accomplishing almost nothing. Building a Personal Brand https://youtu.be/Y7QTUoNRsH4 Website: https://www.FancyQuantNation.com Quant t-shirts, mugs, and hoodies: https://www.teespring.com/stores/fancy-quant Connect with me: https://www.linkedin.com/in/dimitri-bianco https://twitter.com/DimitriBianco
https://www.youtube.com/watch?v=sF-W8xrxOb0
2022/06/26
2
5
Why Lie to Get Someone Hired?
Open
Dimitri Bianco
After discussing on the podcast about building a personal brand someone asked the question, "why lie" if we know it is bad for our brand? Well to get friends hired. Unfortunately these individuals help enough people to stay in the industry. A lot of favors go around that really shouldn't. In this video I even give a real world example of this hiring process where unqualified people are paid large sums of money and end up accomplishing almost nothing. Building a Personal Brand https://youtu.be/Y7QTUoNRsH4 Website: https://www.FancyQuantNation.com Quant t-shirts, mugs, and hoodies: https://www.teespring.com/stores/fancy-quant Connect with me: https://www.linkedin.com/in/dimitri-bianco https://twitter.com/DimitriBianco
https://www.youtube.com/watch?v=sF-W8xrxOb0
2022/06/25
0
0
Backtesting Trading Strategies | An Introduction
Open
Quantra
An introduction video for the course Backtesting Trading Strategies: https://quantra.quantinsti.com/course/backtesting-trading-strategies Welcome to this video on Backtesting Trading Strategies! At some point in your trading journey, you may have experienced, or at least heard, that the vast majority of traders often lose money. They lose money not because they lack an understanding of the market. But, simply because their trading decisions are not based on sound research and tested trading methods. For illustration, here is a chart of the close price series of a stock. Based on this chart, if you were to take a position in this stock today, what would your position be? You may suggest that the price series looks bullish and would like to buy the asset here. On the other hand, you could also argue that the stock’s price looks overvalued at this point and hence, you would consider selling. The truth is, no matter how long you spend trying to make up your mind, neither buying nor selling would be the right decision. This is because the decision to buy/sell here is not based on any strong underlying logic, but rather, it is loosely based on your intuition and subjective analysis. Most traders often make this very same mistake. They make trading decisions based on emotions in hope of making huge profits quickly and end up taking huge losses. However, in the long run, they realize an important insight. This insight is that their chances of getting better and consistent results imp
https://www.youtube.com/watch?v=HguZ8wMh0nE
2022/06/24
119
5
Labelling Techniques in Trading: Filters and Fixed Time
Open
Hudson & Thames
Learn more: www.mlfinlab.com We explore 5 types of filters and introduce the idea of the classic, fixed time horizon labelling technique used in financial machine learning. 1. Event-based 2. Technical 3. Structural breaks 4. Market microstructural 5. Specific signals
https://www.youtube.com/watch?v=hraFWjK3Bes
2022/06/21
25
0
Lessons from Bad Managers
Open
Dimitri Bianco
Last week's episode was on lessons I learned from good managers and today we discuss lessons from bad managers. Many of the key issues here really come down to being an honest and transparent person (lessons we learned in the episode about building a personal brand). Not doing work and calling people out during meetings is simply bad behavior especially when you are the manager.
https://www.youtube.com/watch?v=lhM2cDsFHJs
2022/06/21
16
5
Matrix Flag Labeling
Open
Hudson & Thames
Learn more: www.mlfinlab.com The matrix flag labeling method is meant to capture trends in financial price data, such as bull and bear flags. A bull flag occurs when a stock’s price rapidly increases, followed by a downwards trending consolidation period, followed by a breakout increase in price confirming the original increase. As defined, “A bull flag pattern is a horizontal or downward sloping flag of consolidation followed by a sharp rise in the positive direction, the breakout.” [Leigh et al. 2002]. Being able to identify the early stages of the breakout process can lead to a profitable strategy of buying the breakout and then selling some number of days later, when the price has theoretically stabilized again.
https://www.youtube.com/watch?v=cEFPuNR_J3M
2022/06/20
164
5
Am I Too OLD for Quant Finance?
Open
Dimitri Bianco
One of the most common questions I get asked is, "am I too old for quantitative finance?" That is a very challenging question to answer but in general "no!" For quants the industry just wants smart people who have the right skills. Website: https://www.FancyQuantNation.com Quant t-shirts, mugs, and hoodies: https://www.teespring.com/stores/fancy-quant Connect with me: https://www.linkedin.com/in/dimitri-bianco https://twitter.com/DimitriBianco
https://www.youtube.com/watch?v=LE4Bs1jcslM
2022/06/19
2381
5
Trend-Scanning Labels
Open
Hudson & Thames
Learn more: www.mlfinlab.com Trend Scanning is both a classification and regression labeling technique introduced by Marcos Lopez de Prado, which allows you to detect the overall trend direction and hold a position until the trend changes.
https://www.youtube.com/watch?v=zxGL2cLFFms
2022/06/15
349
5
Lessons from Good Managers
Open
Dimitri Bianco
Over the years of working I have worked for a few managers and have witnessed a lot of managers of a variety of teams. In today's podcast episode I am discussing the lessons I have learned from good managers. Some of the main lessons are about taking time to make big decisions (time has value) and take a real interest in your team members. Next week's episode will be me discussing lessons I have learned from bad managers. Website: https://www.FancyQuantNation.com Quant t-shirts, mugs, and hoodies: https://www.teespring.com/stores/fancy-quant Connect with me: https://www.linkedin.com/in/dimitri-bianco https://twitter.com/DimitriBianco
https://www.youtube.com/watch?v=KveQb25tguM
2022/06/14
832
5
Labelling Techniques in Trading: Triple-Barrier and Meta-Labelling
Open
Hudson & Thames
Learn more: www.mlfinlab.com The idea behind the triple-barrier method is that we have three barriers: an upper barrier, a lower barrier, and a vertical barrier. The upper barrier represents the threshold an observation’s return needs to reach in order to be considered a buying opportunity (a label of 1), and the lower barrier represents the threshold an observation’s return needs to reach in order to be considered a selling opportunity (a label of -1), and the vertical barrier represents the amount of time an observation has to reach its given return in either direction before it is given a label of 0.
https://www.youtube.com/watch?v=mC53d7QhxEw
2022/06/14
302
5
The Peter Carr Memorial Conference: Dilip Madan
Open
NYU Tandon School of Engineering
"The Economics of Time as it is Embedded in the Prices of Options"
https://www.youtube.com/watch?v=ZlCXHgglMw4
2022/06/13
2
0
How to download stock market data in Python?
Open
Quantra
There are many times when traders are faced with certain questions that block their progress. Questions such as - Where can I get the market data (historical/real-time) and other data from? How to download stock data in Python? This session focuses on sharing details of all the authentic and Real-time data providers, and how to use them in Python. When you come to algorithmic trading the first hurdle you might face is “how do I get stock data?”. First of all your broker can provide you with data through API. So either you can get data from your broker or you can get data from an external data vendor. They generally provide the data through APIs and you can access that API through Python. You can also import CSV into Python or use the libraries like Yahoo Finance. Method #1 - Import data from CSV to Python Method #2 - Getting data from Yahoo Finance The examples are mentioned in the video and explain how you can get data if the data is already saved in the form of csv. OR you can get the same data through yahoo finance by importing the yahoo finance library. If you have any queries feel free to mention them in the comment section and keep learning! -------------------------------------------------------------------- Recommended resources for learning Getting Market Data: Stocks, Crypto, News & Fundamental | FREE Course https://quantra.quantinsti.com/course/getting-market-data FREE Course to learn Python and use it to analyze financial data sets https://quantra.quantinsti
https://www.youtube.com/watch?v=CwKAOXR-23M
2022/06/13
157
5
Machine Learning Models for the Interest Rates: Day 2
Open
Quants Hub & BTRM
Session Two/Day 2: Machine Learning Models in Q- and P-Measure Wednesday 8th June: 15.00 - 17.00 BST Timing: each session 2 hours with 5 min coffee break. One factor short rate models Classical time-homogeneous one factor short rate models (Vasicek, CIR, etc.) Classical arbitrage-free one factor short rate models (HW, CIR++, etc.) Autoencoder one factor short rate models in Q- and P-measure Market implied and historical calibration Two factor short rate models Classical two factor short rate models (HW2F/G2, CIR2++, etc.) Autoencoder two factor short rate models in Q- and P-measure Market implied and historical calibration Forward rate models Classical forward rate models (HJM, LMM) Autoencoder forward rate models in Q-measure Market implied calibration Term rate models Classical term rate models (AFNS, Factor HJM) Autoencoder term rate models in P-measure Historical calibration Hands-on examples with Python Autoencoder short rate model in Q- and P-measure Autoencoder forward rate model in Q-measure Autoencoder term rate model in P-measure
https://www.youtube.com/watch?v=D5neua42zy0
2022/06/13
0
0
Machine Learning Models for the Interest Rates: Day 1
Open
Quants Hub & BTRM
Machine Learning Models for the Interest Rates Session One/Day 1: Variational Autoencoder (VAE) for the Yield Curve Tuesday 7th June: 15.00 - 17.00 BST VAE architecture The roles of encoder and decoder Deliberately introducing uncertainty in reconstruction Loss function and optimization loop Reconstruction with VAE Generation with VAE VAE for the yield curve Curve representation Training on historical data One-hot encoding of currency VAE with dimensional latent space VAE with separable two dimensional latent space VAE with non-separable two dimensional latent space Comparison to Nelson-Siegel (NS) and Nelson-Siegel-Svensson (NSS) basis Hands-on examples with Python VAE for handwritten digits from the MNIST dataset VAE for the yield curve
https://www.youtube.com/watch?v=gmeCT8DVJRo
2022/06/13
2
0
Finance Undergrad to Quant Finance Career
Open
Dimitri Bianco
How can you go from a finance undergrad to a quantitative finance career? This is not an easy jump. Skill wise you are unprepared and you need to do something about it. Below are some possible paths. 1) Add a math minor then go for a quant masters or other quantitative masters. 2) Get a quant masters based in a business school who accepts a wide range of undergrad degrees. 3) Get a quantitative masters in another area (math, applied economics, or CS). This can require other prerequisite courses which you might need to take as an undergrad. 4) Get a PhD in something quantitative. Finance and economics can be a possible path but you'll need to learn the missing math, stats, and CS skills required to work in quantitative finance. All paths will require self-studying to increase your odds at landing a job. All of the paths above should aim to gain the same diverse skill set of math, statistics, computer science, and financial application. There are NO shortcuts to quant finance or life! A Primer for the Mathematics of Financial Engineering (affiliate link): https://amzn.to/3NKB6RP Website: https://www.FancyQuantNation.com Quant t-shirts, mugs, and hoodies: https://www.teespring.com/stores/fancy-quant Connect with me: https://www.linkedin.com/in/dimitri-bianco https://twitter.com/DimitriBianco
https://www.youtube.com/watch?v=UK2V07JLU5c
2022/06/12
1731
5
The Peter Carr Memorial Conference: Julien Guyon
Open
NYU Tandon School of Engineering
"Volatility is (Mostly) Path-Dependent"
https://www.youtube.com/watch?v=I7tqzI65nmk
2022/06/10
0
0
The Peter Carr Memorial Conference: Claudio Tebaldi
Open
NYU Tandon School of Engineering
"Financial Interpretation of Feller’s Factorization"
https://www.youtube.com/watch?v=FU6MqKQ1Cf0
2022/06/10
12
0
The Peter Carr Memorial Conference: Pasquale Cirillo
Open
NYU Tandon School of Engineering
"Pseudo Sums, Contingent Claims and a Generalized Memoryless Property"
https://www.youtube.com/watch?v=4K9qAE62_wc
2022/06/10
25
5
The Peter Carr Memorial Conference: Bruno Dupire
Open
NYU Tandon School of Engineering
"Revisiting Black-Scholes"
https://www.youtube.com/watch?v=tKTOOPLdAtE
2022/06/10
31
5
The Peter Carr Memorial Conference: Jim Gatheral
Open
NYU Tandon School of Engineering
"Peter Carr and the variance contract"
https://www.youtube.com/watch?v=m54MgStG6i8
2022/06/10
60
0
The Peter Carr Memorial Conference: Cody Hyndman
Open
NYU Tandon School of Engineering
"Convolution-FFT for Option Pricing in the Heston Model"
https://www.youtube.com/watch?v=HA24PZZLA5Q
2022/06/10
7
0
The Peter Carr Memorial Conference: Kevin Atteson
Open
NYU Tandon School of Engineering
"Maximum Drawdown Derivatives at a Hitting Time"
https://www.youtube.com/watch?v=NSFdUKTHprc
2022/06/10
4
0
The Peter Carr Memorial Conference: Andrey Itkin
Open
NYU Tandon School of Engineering
"Semi-Analytical Pricing of Barrier Options in the Time-Dependent Heston Model"
https://www.youtube.com/watch?v=UxYmz7a0mXo
2022/06/10
14
0
The Peter Carr Memorial Conference: Stephan Sturm
Open
NYU Tandon School of Engineering
"When to Sell and Asset?-A Distribution Builder Approach"
https://www.youtube.com/watch?v=JrDdViE2pLM
2022/06/10
9
0
The Peter Carr Memorial Conference: Douglas Costa
Open
NYU Tandon School of Engineering
"Optionality as a Binary Operation"
https://www.youtube.com/watch?v=ZMwHziPcQgE
2022/06/10
11
0
The Peter Carr Memorial Conference: Sébastien Bossu
Open
NYU Tandon School of Engineering
"Generalizations of Carr-Madan Formula for Option Decomposition"
https://www.youtube.com/watch?v=58IZgIWroxs
2022/06/10
16
0
The Peter Carr Memorial Conference: Ségolène Dessertine-Panhard and Yash Shah
Open
NYU Tandon School of Engineering
"Evolution of Forecasting to Tackle Business Problems: From Standard textbook Time Series Models to State of the Art Algorithms, Ensembling and Interpretability"
https://www.youtube.com/watch?v=Lg-GWknsNOM
2022/06/10
22
0
The Peter Carr Memorial Conference: Bruno Kamdem
Open
NYU Tandon School of Engineering
"Tradable Carbon Permit Auctions Under Regulation and Competition"
https://www.youtube.com/watch?v=oWCCuzYiAQc
2022/06/10
20
0
The Peter Carr Memorial Conference: Umberto Cherubini
Open
NYU Tandon School of Engineering
"Generalizing Compounding and Growth Optimal Portfolios: Reconciling Kelly and Samuelson"
https://www.youtube.com/watch?v=UT6PSs6K4P0
2022/06/10
29
5
The Peter Carr Memorial Conference: Nassim Nicholas Taleb
Open
NYU Tandon School of Engineering
https://www.youtube.com/watch?v=pgSTJlMRHPI
2022/06/10
0
0
Steps to deploy your trading strategy in live markets
Open
Quantra
In this video, we explain the when and how of deploying your backtested trading strategy in the live markets. Having a prior hand experience in trading does not assure getting good results while deploying your backtested strategy in the live markets. Here are a few factors you should consider before going live with your trading strategy: Forward Testing - paper trade in the live market Analyze the Strategy performance Release after Optimization If you have a strategy with great backtesting results can you deploy it in the live markets? Having good backtesting results doesn't mean that you're going to get the same results in live trading. You need to do forward testing - that means, you need to do Paper Trading in the live market which is a kind of simulation. Once you did paper trading and once the results are satisfactory and only then you can move to live trading. When you're doing forward testing you can also optimize the strategy by changing the stop-loss parameters and changing the take profit parameters etc. and optimize it. The problem here is the market changes market moves through different phases, for example, global events and internal events or economic events like macroeconomic data etc. This can spark a change in the behavior of the market, for example, extremely bullish macroeconomic news can start a bullish trend for you. If you have not tested your strategy in a business phase, it might not give you the same results. You need to understand what kind of market
https://www.youtube.com/watch?v=ed4xo8Da1Qs
2022/06/10
73
5
How to Backtest a Strategy? | Quantra Group Learning Session
Open
Quantra
This video focuses on the ways to backtest your trading strategy, even if you do not know to code. There are 3 ways to backtest trading strategy: Use pre-existing Python Library for backtesting i.e Backtrader. Code your own Backtester Use cloud-based research engines like BLUESHIFT - A Free backtesting platform While starting algorithmic trading you might have strategies in hand from prior experiences with manual trading and want to backtest them, to understand how they perform. For that, you can either use pre-existing libraries like Backtrader, a Python package or a Free backtesting platform named Blueshift. Method #1 - Using pre-existing libraries like Backtrader You can easily install Backtrader and do your backtesting or you can code your own practice. Method #2 - Backtesting your own code Backtesting on your own code is the most optimum way because you have full control of it and you can also change the way the backtest is done, which is exactly what is taught to you in the course Python for Trading! In this course we have a separate section on backtesting and and code is available there. We created several functions to create signals create strategies, practised them across several years and analyzed the performance. You can find the link below. Method #2 - Use Cloud-based research engines like BLUESHIFT Another way is to use Cloud-based research engines like BLUESHIFT, where everything is coded for you. You just need to code your strategy and select options to back to
https://www.youtube.com/watch?v=6KcrHmA6LOU
2022/06/10
66
5
Code your indicators in Python | Quantra Group Learning Session
Open
Quantra
How to create Technical Indicators in Python Code? This is one of the most commonly asked questions by the Manual Traders trying to do Algorithmic Trading. This video demonstrates how we can use different Python libraries to create technical analysis. The most commonly used Python libraries are: Standard Libraries like Pandas & NumPy Dedicated Libraries like Ta-lib, & Pandas-ta How to code technical analysis indicators in python? This is one of the most commonly asked questions by the people who are converting from manual traders to algorithmic traders. Generally, when retail trader does manual trading they tend to use technical analysis and technical indicators. It takes 90% of their research while doing manual trading. They might select it from their trading workstation and just do visual analysis. But when you do it in Python, you import the data, import the libraries related to this and do your calculations. There are two ways: 1. Either you can use Standard libraries like Pandas for numerical calculations. 2. If you want to use a technical indicator on stock, if you know the formulas, or know how it is constructed you can code it yourself. Or, you can also use standard libraries created for technical analysis like Ta-lib (technical analysis library), a fantastic library in Python for technical analysis. These two are the most commonly used technical analysis methods in python. The video explains in detail, the steps to create technical indicators. Be sure to check it out
https://www.youtube.com/watch?v=InFz_-j6qTs
2022/06/10
50
5
Get Stock Data using Python | Quantra Group Learning Session
Open
Quantra
There are many times when traders are faced with certain questions that block their progress. Questions such as - Where can I get the market data (historical/real-time) and other data from? How to download stock data in Python? This session focuses on sharing details of all the authentic and Real-time data providers, and how to use them in Python. When you come to algorithmic trading the first hurdle you might face is “how do I get stock data?”. First of all your broker can provide you with data through API. So either you can get data from your broker or you can get data from an external data vendor. They generally provide the data through APIs and you can access that API through Python. You can also import CSV into Python or use the libraries like Yahoo Finance. Method #1 - Import data from CSV to Python Method #2 - Getting data from Yahoo Finance The examples are mentioned in the video and explain how you can get data if the data is already saved in the form of csv. OR you can get the same data through yahoo finance by importing the yahoo finance library. If you have any queries feel free to mention them in the comment section and keep learning! -------------------------------------------------------------------- Recommended resources for learning Getting Market Data: Stocks, Crypto, News & Fundamental | FREE Course https://quantra.quantinsti.com/course/getting-market-data FREE Course to learn Python and use it to analyze financial data sets https://quantra.quantinsti
https://www.youtube.com/watch?v=-77YymLxk1M
2022/06/10
19
5
Difference between NumPy and Pandas | Quantra Group Learning Session
Open
Quantra
What is NumPy? What is Pandas? What is the difference between NumPy and Pandas? Have you started trading using Python and wondering what these terms mean? Well, one must have a sound knowledge of which Python library would benefit them. Python has a huge collection of libraries that can be used for various functionalities like computing, machine learning, visualizations, etc. This video discusses the difference between NumPy and Pandas, their functionalities, and where we can use them. When people start working with python, especially in trading, they tend to import NumPy sometimes and Pandas sometimes. They get confused if they are the same or if there is any difference. Pandas is built on top of NumPy so earlier uh python used to have only NumPy but when data analysts used to analyze the data they created efficient ways to import the data and manipulate the data. This led to the creation of Pandas and the power of numbers is unleashed. So both Pandas and NumPy go hand in hand having specific functionality where they shine. For example: If you are working with the tabular data, it is preferable to use Pandas. The power tools of pandas are series and data frames where you can store one-dimensional data in series and two-dimensional data and data frames. So if you have close prices of a stock like Apple (brand) you can just save it in series or if you have multiple columns with OHLCV data (Open, High, Low, Close and Volume), you can create and store the data in the tabular dat
https://www.youtube.com/watch?v=X71uc81ap8c
2022/06/10
19
0
Why is Python preferred over other languages in Quantitative Finance?
Open
Quantra
Are you one of those, who are wondering about “How to use Python for trading?”, or “How to make profits out of manual trading?”. Then this video is just for you! Get introduced to the best trading platforms as well as some of the most preferred trading platforms. Why do we prefer python for automated trading or algorithmic trading? We have many options, basically, you can do it in python or you can do it in C++ or even you can do it with MATLAB. But, one of the primary reasons why we prefer python is that it is free and open source. So you don't need to have any license to use python and you can even use it for commercial purposes, so for that reason, we use python for algorithmic trading. It is a cross-platform which means the code you create in python is common across all the platforms say, Windows, Linux, Macintosh, or if you have an access to a supercomputer you can use the same code you don't need to change the single line of code and it works same for smart devices or smartphones as well. Python is easy to learn compared to other programming languages, it is easy to use as well and widely accessible. Anyone from a non-programming background can understand at least 30% to 40% of the code. Python has shorter code if you compare it with the second most used code which is C++. The reason behind python having shorter codes is that it has a wide range of support libraries. For example: If you want to calculate something like the mean of the stock price you don't need to code
https://www.youtube.com/watch?v=KGk9rxD9coE
2022/06/10
27
0
Tail-Set Labels
Open
Hudson & Thames
Learn more: www.mlfinlab.com Tail set labels are a classification labeling technique introduced in the following paper: Huerta, R., Corbacho, F. and Elkan, C., 2013. Nonlinear support vector machines can systematically identify stocks with high and low future returns. Algorithmic Finance, 2(1), pp.45-58.
https://www.youtube.com/watch?v=2oebNnhih-U
2022/06/09
6
0
Feature Importance: The Model Fingerprint and Shapley Values
Open
Hudson & Thames
Learn more: www.mlfinlab.com Model Fingerprint algorithm decomposes feature impact on linear, non-linear, and pairwise interaction effects. The algorithm was described in Li, Turkington, Yazdani "Beyond the Black Box: An Intuitive Approach to Investment Prediction with Machine Learning" Shapley Feature Importance is a game-theory approach applied to estimate the importance of a feature.
https://www.youtube.com/watch?v=CikuKuituqY
2022/06/08
5
5
Building a Personal Brand
Open
Dimitri Bianco
I often see gimmicky posts or videos about building a personal brand. It is usually about generating a lot of easy worthless content and adding professional headshots and being active in groups on LinkedIn. LinkedIn is a great place to start however your brand really starts with who you are as a person. Being honest and fair at your day job will bring back much more value in promotions and job opportunities than re-posting how to do something or patting everyone on the back. Now LinkedIn is a great place to help build your brand but I would focus on quality content, questions, and comments over quantity. Website: https://www.FancyQuantNation.com Quant t-shirts, mugs, and hoodies: https://www.teespring.com/stores/fancy-quant Connect with me: https://www.linkedin.com/in/dimitri-bianco https://twitter.com/DimitriBianco
https://www.youtube.com/watch?v=Y7QTUoNRsH4
2022/06/07
26
5
Portfolio Optimization Workshop
Open
Hudson & Thames
Learn more at: https://hudsonthames.org/portfoliolab/ In this workshop we cover all of the concepts introduced in the Portfolio Optimization playlist, namely: how to apply mean-variance, critical line algorithm, theory implied correlation, and machine learning techniques such as nested clustered optimization, hierarchical risk parity, and hierarchical equal risk contribution.
https://www.youtube.com/watch?v=OeqIGC-WTWo
2022/06/07
396
5
Trailer: Portfolio Optimization Workshop
Open
Hudson & Thames
A quick overview of what is covered in out Portfolio Optimization Workshop.
https://www.youtube.com/watch?v=cpTKrDzmcIg
2022/06/07
11
5
SoFiE Seminar with Emi Nakamura and Richard Crump
Open
Society for Financial Econometrics
Host: Ekaterina Smetanina (The University of Chicago Booth School of Business) Presenter: Emi Nakamura (University of California, Berkeley) Paper: "Learning about the Long Run" Discussant: Richard Crump (Federal Reserve Bank of New York) Date: June 6, 2022 The Society for Financial Econometrics Seminar Series features bi-monthly presentations of cutting-edge research by leading scholars in financial econometrics. Presentations are followed by discussion and audience participation. The SoFiE Seminar series is organized and moderated by Eric Ghysels, Ekaterina Smetanina and Dacheng Xiu. SoFiE Seminar Series events are held as Zoom webinars and are open to all. If you would like to receive updates about these events, please email sofie@stern.nyu.edu and request to join our mailing list. Otherwise, please visit the SoFiE website, sofie.stern.nyu.edu, for the most up-to-date list of our events. The Society for Financial Econometrics (SoFiE) is a global network of academics and practitioners dedicated to sharing research and ideas in the fast-growing field of financial econometrics. It is an independent non-profit membership organization, currently housed at New York University. Members receive a complimentary subscription and waived manuscript submission fee to SoFiE's partner publication, the Journal of Financial Econometrics. Other benefits of membership in the Society include the opportunity to submit papers to be reviewed by our program committee for our co-sponsored joint eve
https://www.youtube.com/watch?v=0eAUfN6sf1g
2022/06/06
4
0
Do You Need an Ivy League Degree?
Open
Dimitri Bianco
A common question I get for quantitative finance careers is, "do I need an Ivy League degree?" The simple answer is no. Ivy league name brand does help in general as it helps to indicate you are smart however not all ivy league programs are specialized in quantitative finance or financial engineering. There are many great graduate programs in quantitative finance which are not ivy league. Website: https://www.FancyQuantNation.com Quant t-shirts, mugs, and hoodies: https://www.teespring.com/stores/fancy-quant Connect with me: https://www.linkedin.com/in/dimitri-bianco https://twitter.com/DimitriBianco
https://www.youtube.com/watch?v=u8D-Z3aAuuI
2022/06/05
31
5
AIFI - Equity Machine Learning Models & Deep Partial Least Squares
Open
Quants Hub & BTRM
Miquel Noguer i Alonso: Equity Machine Learning Models We examine in this paper the training and test set performance of several equity factor models with a dataset of 20 years of data, 1,200 stocks and 100 factors. First, we examine several models to forecast expected returns, which can be used as baselines for more complex models:·Linear regression, Linear regression with an L1penalty (lasso), Constrained linear regression and xgboost and Artificial Neural networks. Second, we present a unified framework for portfolio construction, leveraging machine learning for the whole pipeline, from the factor data to the portfolio weights, which scales to a large number of assets and predictors. The results we obtain are interesting and non trivial to interpret, non linear models models offer a more balanced outcome considering test set sharpe ratio and turnover but linear unconstrained models show a good performance in the test set. Slides: https://www.wbstraining.com/wp-content/uploads/2022/06/Equity_Machine_Learning_Models_2022_Def.pdf Matthew Francis Dixon: Deep Partial Least Squares for Cross-Sectional Financial Modeling Across hedge funds, asset management, and proprietary trading firms, it is commonplace to use supervised learning for asset allocations and trade signal generation by performing ``feature engineering''. This often leads to a high dimensional input space. We present a high dimensional data reduction technique which uses partial least squares within deep learning.
https://www.youtube.com/watch?v=ZPGtgKejj1M
2022/06/04
0
0
How to fetch daily stock price data using Yahoo finance?
Open
Quantra
How do you retrieve stock market data from Yahoo finance using the finance package? This video guides you with just that. This video is part of the course: https://quantra.quantinsti.com/course/getting-market-data If you prefer to go through the notebook then you can skip this video: https://quantra.quantinsti.com/startCourseDetails?cid=190§ion_no=2&unit_no=1&course_type=paid&unit_type=Notebook It covers: 0:15 Why do we need historical price data? 0:31 Key Takeaways 0:43 Importing Pandas and finance packages 1:01 How to get the price data? 1:30 How to get the data for Apple (APPL)? 2:52 Get data for stocks 3:10 Live practise using the notebook 3:33 Adjusted data 3:48 How to get adjusted open, high, low, and volume? 4:14 Downloading the adjusted price data for different assets Why do we need historical stock price data? Access to historical price data is a necessity when you plan to create and backtest your strategy. There are several web sources and Python packages available to download the data. In this notebook, you will learn how to download the stock price data from Yahoo Finance. We will see how to download the Data and Adjusted Price Data using yahoo finance. Let's start by importing pandas and yfinance packages. You can also assign an alias to these packages. We have assigned an alias of pd for pandas and yf for yfinance. You can use these aliases to call all the methods of that package rather than writing the full name every time. How to get the price d
https://www.youtube.com/watch?v=ruwdxcUsmKU
2022/06/03
94
5
Hierarchical Equal Risk Contribution (HERC)
Open
Hudson & Thames
Learn more at: https://hudsonthames.org/portfoliolab/ – Dr. Thomas Raffinot: As diversification is the only free lunch in finance, the Hierarchical Equal Risk Contribution Portfolio (HERC) aims at diversifying capital allocation and risk allocation. Briefly, the principle is to retain the correlations that really matter and once the assets are hierarchically clustered, a capital allocation is estimated. HERC allocates capital within and across the “right” number of clusters of assets at multiple hierarchical levels. This Top-Down recursive division is based on the shape of the dendrogram, the optimal number of clusters and follows an Equal Risk Contribution allocation. Contrary to modern portfolio optimization techniques, HERC portfolios are diversified and outperform out-of-sample.
https://www.youtube.com/watch?v=k1Cjw9z1AKg
2022/06/02
39
5
No, Covid is not an "old" person's problem.
Open
N N Taleb's Probability Moocs
Covid increases mortality rates proportionally. And if one considers such diseases dynamically they can reduce life expectancy even more, hitting the young disproportionally. Telling a 40 y.o. "you have a 10% higher probability of death" surprises them. Many "young" people fail to think dynamically, and realize they will be older some day. Think of a 30 y.o. saving for the future, but not considering the effect of the pandemic of 2050.
https://www.youtube.com/watch?v=iN1Qtd1vVbI
2022/06/01
491
5
QuantUniversity Guest Lecture series: The Disagreement Problem in Explainable Machine Learning
Open
QuantUniversity Channel
Powered by Restream https://restre.am/yt Abstract : As various post hoc explanation methods are increasingly being leveraged to explain complex models in high-stakes settings, it becomes critical to develop a deeper understanding of if and when the explanations output by these methods disagree with each other, and how such disagreements are resolved in practice. However, there is little to no research that provides answers to these critical questions. In our work, we introduce and study the disagreement problem in explainable machine learning. More specifically, we formalize the notion of disagreement between explanations, analyze how often such disagreements occur in practice, and how do practitioners resolve these disagreements. To this end, we first conduct interviews with data scientists to understand what constitutes disagreement between explanations generated by different methods for the same model prediction, and introduce a novel quantitative framework to formalize this understanding. We then leverage this framework to carry out a rigorous empirical analysis with four real-world datasets, six state-of-the-art post hoc explanation methods, and eight different predictive models, to measure the extent of disagreement between the explanations generated by various popular explanation methods. In addition, we carry out an online user study with data scientists to understand how they resolve the aforementioned disagreements. Our results indicate that state-of-the-art explana
https://www.youtube.com/watch?v=9rV-0D0nGMs
2022/06/01
6
5
Is Hiring Fair: Truth from the Inside
Open
Dimitri Bianco
Hiring for any job is extremely challenging. Getting hired as an employee is also extremely challenging. Today I cover the biggest issue on why firms can't find the right candidates as well as why individuals who are fully qualified can't find good jobs. We'll discuss job descriptions, salaries and budget constraints, and resumes.
https://www.youtube.com/watch?v=a9YIxLb5Slg
2022/05/31
8
5
Data representations for neural networks
Open
Abhishek Thakur
This is a video in the Python Deep Learning series which is a book by François Chollet. Deep Learning with Python (2nd Edition, by Francois Chollet). If you don't have the book, you can buy it here: https://bit.ly/keras2nd. In this video, talk about tensors, ranks, scalers, and vectors, and look at different data types for deep learning. Please subscribe and like the video to help me keep motivated to make awesome videos like this one. :) My book, Approaching (Almost) Any Machine Learning problem, is available for free here: https://bit.ly/approachingml Follow me on: Twitter: https://twitter.com/abhi1thakur LinkedIn: https://www.linkedin.com/in/abhi1thakur/ Kaggle: https://kaggle.com/abhishek
https://www.youtube.com/watch?v=-jCA0ctrLh0
2022/05/31
974
5
Load 50 more
TOP