All decks
  • A Machine Learning Approach to Systematic Global Macro Strategies

    From the time of Benjamin Graham to Jeremy Grantham, using macroeconomic data in asset allocation has been the most universally accepted way of tactical asset allocation. However, without a machine learning foundation, global macro has often been considered an art and not a science. In this webinar, we will give a preview to use of macro-economic data for asset allocation in a deep learning framework. Think of this as a "RoboWarren" which is able to look at over 100 macro-economic indicators to predict if a stock market correction is imminent.

  • Using recommender systems in the Chief Investment Office

    Gaurav Chakravorty explains how recommender systems can be utilized for investment management and details how AI and deep learning are used in trading today. Gaurav begins by diving into chief investment offices, which are growing their in-house machine learning teams to fine-tune their allocation, using both traditional and alternative strategies. Gaurav shares a novel approach to deciding asset and strategy allocations, inspired by research in recommender systems. Gaurav then explores the application of deep learning in trading, discussing useful techniques for AI-driven asset managers as well as the blind alleys they’ve gone down. With these cases as context, Gaurav addresses some of the technical and operational aspects of AI, such as key bottlenecks in training and inference, the software frameworks and hardware platforms that are most useful for those workloads, deployments, the scaling challenges, and the key drivers of the cost.

  • Building Chatbots

    In this presentation, we will talk about the machine learning and system design challenges of building chatbots

  • Building data set pipelines for deep learning strategies

    Over the last decade deep learning has had tremendous success in pushing state of the art in numerous domains such as computer vision, natural language processing, machine translation and speech recognition. All of these domains are characterized by large quantities of data. In order to leverage deep learning research to the fullest, many progressive asset managers are experimenting with different approaches to generate and use hypothetical data so that the models can learn what to do in scenarios that the markets haven't seen yet.

  • Use of Hypothetical Data in Machine Learning Trading Strategies

    Over the last decade deep learning has had tremendous success in pushing state of the art in numerous domains such as computer vision, natural language processing, machine translation and speech recognition. All of these domains are characterized by large quantities of data. In finance, however, even 20 years of end-of-day data is merely 5,000 points and any data-driven trading strategy is only as good as the data itself. In order to leverage deep learning research to the fullest, many progressive asset managers are experimenting with different approaches to generate and use hypothetical data so that the models can learn what to do in scenarios that the markets haven't seen yet. In this webinar, we will discuss use of synthetic/hypothetical data that can potentially solve this problem.

  • The confluence of high frequency trading and machine learning infrastructure

    We will talk about the machine learning infrastructure needed in high frequency trading. We will show the algorithmic and infrastructure innovations that helped us derive alpha from market information faster than others.

  • Active Investing vs Buy and Hold

    Our co-founder Mansi Singhal will discuss the common myths that surround active investing, among them: the high trading costs and used only for outright alpha. We will challenge these common fallacies and discuss how active investing is being severely misunderstood by many investors. Active investing can play a crucial role in portfolio management. We will demonstrate how some of the biggest market players use active investing to: 1- Target constant risk. 2-Defend against market crashes. 3- Reduce costs and improve performance via methods like rebalancing, tax-loss harvesting and algorithmic execution.

  • Using Artificial Intelligence in the Chief Investment Office

    Gaurav Chakravorty, co-founder and Chief Investment Officer at qplum, will discuss how Deep Learning can be used in global tactical asset allocation. We will show how this investment strategy compares to a traditional institutional investing benchmark as well as qplum's US investor index. We believe that Deep Learning will provide a huge contribution to asset management in its utility for core tactical asset allocation rather than indirectly predicting returns.

  • Using data-science to reduce tax impact

    In this presentation, we will debunk the myth that buy-and-hold is far superior to data-science based investing. We will show how to build an investment system for taxable accounts that directly optimizes post-tax returns.

  • ETFs versus single stocks

    Gaurav Chakravorty, co-founder and Chief Investment Officer at qplum, will discuss how market dynamics have changed in favor of ETFs versus stocks in the last five years. There is a lot more opportunity to realize returns in ETF trading than stocks now.

  • Tactical Asset Allocation using Deep Learning

    Gaurav Chakravorty, co-founder and Chief Investment Officer at qplum, will discuss how Deep Learning can be used in global tactical asset allocation. We will show how this investment strategy compares to a traditional institutional investing benchmark as well as qplum's US investor index. We believe that Deep Learning will provide a huge contribution to asset management in its utility for core tactical asset allocation rather than indirectly predicting returns.

  • AI is the future of asset management

    In this talk at AIM Summit Dubai, Gaurav will talk about why AI is the future of asset management, why are we talking about it now, what has changed, and how can investors separate the fakers from the makers

  • How do you match up against the average U.S. investor?

    The U.S. investor doesn't invest only in the S&P 500 Index. Contrary to what real estate agents might tell you, U.S. investors don't just load up on real estate either. In this presentation, we look at publicly available Federal Reserve and BLS data to gauge what investors actually invest in. We will make an index, that is the right benchmark for US investors.

  • The next ten years: Deep Learning in Trading

    In this talk at Univ. of Pennsylvania, Gaurav will talk about some job trends in financial services to start and cover the transformational impact of A.I. and Deep Learning in making trading a scientific process. Deep learning has been very successful in social sciences and specially areas where there is a lot of data. Trading and investment management fits this paradigm perfectly. It is a social science and not a pure science, and we are generating petabytes of data everyday making it tough to learn from. With the advent of Deep Learning and Big Data technologies for efficient computation, we are finally able to use the same methods in investment management as we would in face recognition or making chatbots. This focus on learning a hierarchical set of concepts is truly making investing a scientific process, a utility.

  • How to model and trade volatility futures

    How to model and trade volatility futures

  • Boosting and Neural Networks

    Petar Maymounkov is one the most brilliant computer scientists of our age. At qplum's FinTech and Data Science meetup he presents techniques that can be applied to learn from a number of ideas in a scientific manner. He shows how to improve a Deep Learning approach with Boosting

  • FinTech in Investment Management

    The new investing landscape where traders are losing jobs and data scientists rule. Why is this happening? What do I need to do to have a job ten years later?

  • Investment Management using Deep Learning and Big Data

    The new investing landscape where traders are losing jobs and data scientists rule. Why is this happening? What do I need to do to have a job ten years later?

  • Choosing the right machine learning algorithm

    We will look at how representation learning is at the heart of choosing the right machine learning algorithm

  • Using deep learning to trade: Practical lessons for technologists

    What kinds of deep learning have we found useful at qplum? Technical and operational aspects of trading using deep learning. Key bottlenecks in training and inference. Software frameworks and which hardware platforms have proven most useful for those workloads. What does a deployment look like? What are the scaling challenges and key drivers of cost? How does devops work when a lot of the dev is handled by machines.

  • Ten year cycle of innovation in trading

    The next ten years are going to be about deep learning. We show what happened in the past and what were the business drivers, and how the business drivers are converging behind making investing a utility powered by Deep Learning

  • Towards the science of investing - Deep Learning

    The next ten years are going to be about deep learning. We show what happened in the past and what were the business drivers, and how the business drivers are converging behind making investing a utility powered by Deep Learning

  • Applying Deep Learning and High Frequency Alpha to Trading

    The next ten years are going to be about deep learning. We show what happened in the past and what were the business drivers, and how the business drivers are converging behind making investing a utility powered by Deep Learning

  • AI and Deep Learning in Trading

    The next ten years are going to be about deep learning. We show what happened in the past and what were the business drivers, and how the business drivers are converging behind making investing a utility powered by Deep Learning

  • US household wealth index

    The US household wealth index is the right index for individual investors to compare themselves to, if they want to see how well they are investing.

  • How to invest in way to reduce the impact of taxes

    How should an investor go about maximizing their post-tax returns, and how we at qplum are helping them do it

  • Execution Algorithms

    Execution algorithms are a class of intraday trading strategies that can help an investor or a portfolio manager try to get the best available price on that day

  • Investing is a science

    In this talk, I'll present a set of ideas, some results and some quizzes that show that we have all the tools necessary to finally make investing a science and not a game or competition.

  • A.I. and Trading an evolving relationship

    We will talk about past attempts to make investing into a science and where are opportunities of Deep Learning and Artificial Intelligence based disruption in portfolio management today.

  • How to remove overfitting in trading

    The main challenge in some fields of applied data-science is to remove overfitting. We will talk about the approaches taken to reduce overfitting over the years ad the state of the art currently.

  • Top strategies in pension fund investing

    How Artificial-Intelligence, FinTech, Liability-Driven-Investing are reshaping the landscape of institutional investing

  • Overview of Deep Learning Architectures

    In this presentation at Data Science + FinTech meetup in Jersey City, Sumit Chopra from Facebook Research, presents an overview of Deep Learning architectures

  • Manifold Learning and applications to Trading

  • The evolution of trading and FPGA

    The evolution of trading, the three sources of returns in financial markets, and the state of the art in trading based on information processing. Olivier Baetz will talk about FPGA and its critical role in high speed trading infrastructure.