Quantitative Finance

Quantitative Finance or Mathematical Finance is applied mathematics with a strong focus on the financial markets. In Quant Finance, especially quant finance for trading firms, the quant seeks to use numerical models from market prices, company or asset fundamental data, and alternative data to develop new trading or investment models. The goal is to provide a new trading model.

CloudQuant provides quantitive financial enthusiast and professionals with free tools to develop new trading models. These crowd researchers develop the trading models and work with quantitative traders to execute the trading strategy. The quant is paid based on a license agreement where the trading strategy receives an allocation and they retain their own intellectual property (the algo.)


$TSLA Split shown in CloudQuant Analysis

$TSLA Skyrocketed Ahead of Stock Split

$TSLA Skyrocketed Ahead of Stock Split Shown in the spikes in the acceleration of change of volatility spread.
Algo Trading powered by Alternative Data Sets

Conversations: Effects of Alternative Data Sets on Trading Algorithms


What effect can alternative data sets have on trading algorithms?

We asked a few of our teammates and systematic traders what the effect of alternative data sets is on trading algos. We thought we could spread some insight as to why our alternative data is so valuable the also developers. We all start using the smallest and most basic data sets, such as the generic S&P500 stock prices. This is all just fine until you want to take your development to the next level. You can delve deeper into predicting the rise and fall of each stock using these specified alternative data sets. CloudQuant offers a wide and expanding variety of these data sets for free, giving our users easy access to alternative data in order to help them improve their trading strategies.
The teammates featured are:
  • Tayloe Draughon- Sr. Product Manager
  • James Chang- Quantitative Portfolio Manager
  • Morgan Slade- CEO
  • Steve Pettinato- Portfolio Manager
  • Paul Tunney- Client Success Manager
Quantamental alternative data

Conversations: Learning Python within CloudQuant

What was your experience like learning Python within CloudQuant?

We asked our portfolio managers and product management teammates who code in Python to explain their starting experiences in programming with Python with CloudQuant. We wanted to share with everyone what encouraged them to keep learning throughout the years. Everyone here codes as part of their job. This includes the CEO all the way down to the interns. We rely on our Backtesting Engine to ensure that trading algorithms work well before committing money to the automated trading strategies. But we also use JupyterLab in our daily work. We generate our reports, monitor our systems, and do all sorts of tasks in Python. Python has overtaken the spreadsheet in CloudQuant. The teammates featured in this video are:
  • Morgan Slade- CEO
  • Tayloe Draughon- Senior Product Manager
  • James Chang- Quantitative Portfolio Manager
  • Rob Ferguson- Quantitative Equity Portfolio Manager
  • Simon Zhang- Quantitative Analyst
Watch this video to gain insight as to what got our amazing coders to where they are.
John "Morgan" Slade

Quants discuss evaluating and adapting their models – Including CloudQuant

In a world where robots, voice recognition and artificial intelligence are growing in importance, Peltz International’s Meet the Quantitative Manager … In January, Morgan Slade participated in a Panel Discussion for Quantitative Fund Managers and how they are adapting their model. This link to the article published by Peltz International after the conference requires registration and a user ID on their web site.
New York

Meet The Niche Manager – Quantitative Managers. January 26, 2018


Peltz International seminar Meet the Niche Manager on January 26, 2018

CloudQuant will be participating in the Peltz International seminar Meet the Niche Manager on January 26, 2018 in New York. Investors will have an opportunity to meet managers they may not be familiar with. Investors will have an opportunity to see the manager in action, thinking on his feet, discuss critical issues relative to the specific strategy. “Niche’ is defined as an alternative investment strategy that is not used by many managers. It may relate to the methodology used and/or the markets traded. In many cases, the correlation to traditional investments will be low. 8:15-8:30     Registration 8:30-9:45     Panel discussion, critical issues relating to the strategy 9:45-10:25    Individual strategy highlights 10:25-11:00  Informal networking   Pre-registration is required. To register, call 212 689 0180 or E: General@peltzinternational.com  

Futures Radio Show interviews Morgan Slade December 12, 2017

CloudQuant’s CEO was interviewed by Anthony Crudele of Futures Radios show to discuss topic including Artificial Intelligence, Machine Learning, and Deep Learning applied to algorithmic trading. Alternative datasets are a major topic of discussion. People are saying that data is being created faster than ever before. That really isn’t true. What is really happening is that data is being captured and stored at a faster rate than ever before. Vendors are now making AltData available for traders to change the way that they interact with the markets. This applies to futures and stocks with the popularity of Deep Learning in algorithmic trading strategy development.

Technical Analysis Library (TA-LIB) for Python Backtesting

Anyone who has ever worked on developing a trading strategy from scratch knows the huge amount of difficulty that is required to get your logic right. … TA-LIB Turbo-Charges Your Research Loop: TA-Lib is widely used by quantitative researchers and software engineers developing automated trading systems and charts. This freely available tool allows you to gather information on over 200 stock market indicators.
Quantitative Strategy, Trading, and Algo Development Industry News

Industry News: Machine Learning and Artificial Intelligence for December 11, 2017

Hedge funds embrace machine learning—up to a point

ARTIFICIAL intelligence (AI) has already changed some activities, including parts of finance like fraud prevention, but not yet fund management and stock-picking. That seems odd: machine learning, a subset of AI that excels at finding patterns and making predictions using reams of data, looks like an ideal tool for the business. Yet well-established “quant” hedge funds in London or New York are often sniffy about its potential. In San Francisco, however, where machine learning is so much part of the furniture the term features unexplained on roadside billboards, a cluster of upstart hedge funds has sprung up in order to exploit these techniques. These new hedgies are modest enough to concede some of their competitors’ points. Babak Hodjat, co-founder of Sentient Technologies, an AI startup with a hedge-fund arm, says that, left to their own devices, machine-learning techniques are prone to “overfit”, ie, to finding peculiar patterns in the specific data they are trained on that do not hold up in the wider world. This is especially true of financial data, … 2017-12-09: https://www.economist.com/news/finance-and-economics/21732147-investing-more-artificial-intelligence-need-not-mean-less-human CloudQuant Thoughts: Traditional hedge fund managers may be concerned with AI and machine learning. CloudQuant embraces it. We have found that the CrowdSourcing model allows for new talent to join in the research activities. A thousand researchers with access to industrial grade historical market data, backtesting tools, and alternative data can discover new ways of trading that a traditional quant at a hedge fund may not see. Our record of allocations demonstrates that this is working well for us.

Demand for AI Talent Turns Once-Staid Conference Into Draft Day

Actors in robot costumes stood in the lobby of the Westin hotel in Long Beach, California on Sunday night, “Intel Inside” stickers displayed on their foam torsos. People posed for selfies before heading to an upstairs ballroom, decorated with neon purple lighting and plush white leather furniture, for an event that was more party than technology panel discussion. This was one of many attempts by Intel Corp. and other giant corporations to curry favor with artificial-intelligence researchers attending one of the world’s biggest AI conferences, turning what was once an academic event into a recruiting frenzy more akin to the National Football League’s draft day. Tech companies are increasingly competing with one another, as well as banks and hedge funds, to hire experts in AI techniques like neural networking, a kind of machine learning loosely based on how the human brain works. These are the skills behind recent advances in computers’ ability to identify objects in images, translate languages, drive cars and spot financial fraud. More changes are in store for many industries and conferences like this week’s one on Neural Information Processing Systems, aka NIPS, are where … 2017-12-06: https://www.bloomberg.com/news/articles/2017-12-06/demand-for-ai-talent-turns-once-staid-conference-into-draft-day CloudQuant Thoughts: It is fun seeing financial firms mentioned alongside the technology firms that you typically expect to see in a conference like this. Anyone in trading will fully understand that trading firms have been very technology-centric for the past decade. The introduction of Machine Learning, Deep Neural Network, and applied AI into the FINTECH discussions, and the recruiting process is not surprising.

This Harvard PhD’s AI Startup Aims to Help Analysts Triple Coverage

…After applying his machine learning programs to central bank policy statements to churn out trading calls, a hedge fund-backed political economy specialist is aiming his sights on corporate earnings announcements. Evan Schnidman, a 31-year-old who set up his own firm after a Harvard University PhD dissertation that looked at the Federal Reserve’s communications, is hoping the approach that lured $3.3 million in a fund-raising roun… 2017-12-11 00:00:00 https://www.bloomberg.com/news/articles/2017-12-11/harvard-phd-s-ai-startup-aims-to-help-analysts-triple-coverage CloudQuant Thoughts: The article ends with “Demand for data scientists and machine-learning professionals in finance ‘far exceeds the current supply,‘” We see that many universities and programs are gearing up to meet this demand. Those that want to learn and practice skills are always welcome to grow their data science and machine-learning skills on our CloudQuant platform.

3 Questions with Dr. Sean Wise of Ryerson Futures Seed Fund

…inancing round. What do you believe the next major innovation in financial technology will be and why? I believe the next major innovation in financial technology will be the wide integration of AI/Machine Learning into customer service chat-bots. The majority of customer service queries are mundane and routine (e.g. I lost my PIN what do I do). This is just an awful job for humans and outsourcing to developing nations has not solved it. Chatbots offer an exponentially better more scalable solution to better customer service. The volume of queries, the routineness of such and the current level of semantic … 2017-12-10 14:05:55-05:00 http://finteknews.com/3-questions-dr-sean-wise-ryerson-futures-seed-fund/ CloudQuant Thoughts: Fintek News interviewed our CEO prior to chatting with Dr. Wise. You can find and compare answers from Dr. Wise with Morgan Slade’s answers by reviewing our earlier inteview at http://finteknews.com/3-questions-john-morgan-slade-cloudquant/

Hedge fund managers embrace innovation amid industry challenges and increased competition

…gin pressures by investing in technology. Forty per cent say they plan to invest in automating manual processes and more than a quarter of managers (27 per cent) have or will be making investments in artificial intelligence and robotics to strengthen their middle and back office. Zeynep Meric-Smith, EMEIA Leader, Hedge Fund Services, Ernst & Youn, says: “Managers with growing businesses will often need to add to their headcount to support the business, but modern advances in technology provide helpful solutions in supporting operating models that add to the bottom line, rather than reduce it.” The need for tec… 2017-12-08 00:00:00 http://www.hedgeweek.com/2017/12/08/259158/hedge-fund-managers-embrace-innovation-amid-industry-challenges-and-increased CloudQuant Thoughts: In this article it says “Investors are looking for managers who can effectively implement next generation data to gain an advantage, according to the survey. Managers are beginning to notice that effective use of data is a key advantage,” CloudQuant firmly believes this. Our crowd researchers are finding alpha in new ways, using new data sets. We believe that our experience is indicative for the future of most investment managers and traders.

Big data solutions to take a bite out of fraud

…nd harnessing the massive quantities of data produced each day, companies hope to uncover potential fraud as it occurs. The most optimistic believe that the predictive capabilities of big data-driven artificial intelligence may someday end online crime altogether. That may well come to pass, but it will be an uphill climb. The current state of affairs The internet represents an ever-larger portion of global retail sales each year. Estimates indicate that e-commerce transactions alone will reach $2.3 trillion dollars this year. Digital platforms also generate enormous amounts of advertising revenue and related busi… 2017-12-08 11:00:34+00:00 http://bigdata-madesimple.com/big-data-solutions-to-take-a-bite-out-of-fraud/#Comment CloudQuant Thoughts: This is another article in the trend of articles talking about using AI, ML, and evolving computer tools and techniques to detect fraud. We recently posted on our blog about these tools and techniques related to Algos and Ethics.  The FINTECH & REGTECH industries have been rather busy in applying AI/ML to fraud. Here are some actions and innovations that we have seen in the world of electronic trading covering regulators and vendors. AI, Algo Trading and the Regulators and Watchdogs AI, Algo Trading, and the Innovative Firms
  • Vertex Analytics with their amazing ability to see patterns in the market data and highlight cheaters.
  • Trading Technologies’ Neurensic product that uses machine learning to catch spoofers, front-runners, layering, pump and dump, and more forms of illegal trading.
  • Edge Financial Technologies and their KillSwitchPlus tool that catches run away algos and limit breaches at the time of the order.
  • Catelas with its surveillance ability to catch collusion between traders or inappropriate use of insider data.

5 Scary Things That Won’t Crash the Market in Next 5 Years

…o the CFA Institute highlighted 5 disruptive forces influencing the future of global investing. I think these forces are vitally important, but will not “crash” the market in the next five years: 1. Artificial intelligence, big data and machine learning will be disruptive forces, but humans will still play an important role in providing investment management and financial advice. Quantitative algorithms are increasingly used to identify past patterns and subtle trends in large sets of data. Quantitative models may be superior to humans in looking through the rearview mirror, but humans still may be better equipped … 2017-12-04 00:00:00 http://techcenter.thinkadvisor.com/2017/12/04/5-scary-things-that-wont-crash-the-market-in-next?ref=hp-blogs CloudQuant Thoughts: We don’t consider big data, AI, or machine learning to be scary. We also agree that we don’t believe that this will be the direct cause of any future market crash.

The Computer That Saved a Vineyard

… fire. He hosed down embers as they flew off the frame. Yet the winery survived the worst disaster in the history of California’s wine country unscathed, because Palmaz wasn’t alone, exactly. He had artificial intelligence on his side. Palmaz Vineyards’ winemaking takes place in an engineered maze of tunnels and domes carved into rock at the base of Napa’s Mount George. Source: Palmaz Vineyards Felix is the nickname for the Fermentation Intelligence Logic Control System (Filcs), software Palmaz engineered to analyze and, eventually, help micromanage the vineyard’s 36 winemaking tanks. Using technology developed b… 2017-12-06 00:00:00 https://www.bloomberg.com/news/articles/2017-12-06/the-computer-that-saved-a-vineyard CloudQuant Thoughts: We will drink to that! We may need to order a case or two for our Holiday party. You can find the vineyard at https://www.palmazvineyards.com/

Microsoft doubles down on its ‘AI for Earth’ initiative, pledging $50M at Paris climate event

…Microsoft today pledged $50 million over five years for an initiative to use artificial intelligence to tackle the world’s most pressing environmental issues. Microsoft President and Chief Legal Officer Brad Smith will detail the company’s commitment to the program, known as AI for Earth, at the One Planet Summit in Paris later today. Started earlier this year, AI for Earth aims to put Microsoft’s vast AI resources in the hands of universities, non-governmental organizations and other groups to… 2017-12-11 11:01:28+00:00 https://www.geekwire.com/2017/microsoft-doubles-ai-earth-initiative-pledging-50m-paris-climate-event/ CloudQuant Thoughts: Private industry is taking initiative and leadership using AI to solve an issue that many are concerned with globally. Nice move Microsoft.

What Does Your Cloud Data Look Like? QuantHouse Is Moving Historical Data On-demand To The Cloud

… also looking at the metadata space. Firms can now take their own trading information and identify better performance strategies for traders, or weed out problems with a particular strategy. Layer in artificial intelligence and machine learning tools and you can see the potential for firms and another phase of competition. QuantHouse moved to bolster its overall service offering with the acquisition of Victory Networks in September, giving it further reach in the high speed network space, especially for hedge funds and asset managers. Feligioni believes his firm is now well positioned for that client base which is … 2017-12-08 00:48:00+00:00 http://www.johnlothiannews.com/2017/12/cloud-data-look-like-quanthouse-moving-cloud/ CloudQuant Thoughts: Nice move QuantHouse. We like what you are doing. We also find that the cloud’s power for computing cycles provides a major opportunity for the industy.

Nasa to hold major announcement after artificial intelligence makes major planet-hunting breakthrough

…ly relate to exoplanets – Earth-sized worlds that orbit around their own stars, and are our best hope of finding alien life. The space agency said that the discovery was made with the help of Google artificial intelligence, which is being used to analyse the data sent down by the telescope. By using machine learning provided by the tech giant, Nasa hopes that it can pick through the possible planets more quickly and hopefully find life-supporting planets sooner. Nasa said that four engineers and scientists would take part in the session. They include Paul Hertz, who leads Nasa’s astrophysics division, a senior Goo… 2017-12-11 08:53:56+00:00 http://www.independent.co.uk/life-style/gadgets-and-tech/news/nasa-announcement-today-latest-kepler-breakthrough-google-ai-artificial-intelligence-a8102966.html CloudQuant Thoughts: We already knew that machine learning is “Out of this world” but this just proves the point.

Apple’s AI Chief Reveals Fresh Details About The Car Project

…researchers to share their work – primarily related to the car project – with the wider scientific community. Apple car project: It can detect objects hidden behind parked cars Speaking at the NIPS machine learning conference (via Wired), Apple’s AI director Ruslan Salakhutdinov provided some previously unpublicized details about the self-driving car technology. He offered a sneak peek into how Apple is using artificial intelligence and machine learning to detect pedestrians and make autonomous driving safer. More than 8,000 people attended the NIPS conference. He demonstrated a system that can identify ob… 2017-12-11 06:43:07-05:00 http://www.valuewalk.com/2017/12/apple-car-project-ruslan-salakhutdinov/#disqus_thread CloudQuant Thoughts: The trend is to be more open with technology. We see it in open source and crowdsourcing. Apple, with a very loyal community of users, always has a great opportunity to be a thought leader and not just an innovation leader. We like seeing them be more open.

Quantitative Brokers Appoints Ralf Roth as CEO

…ch he will join. Roth will begin as CEO effective December 18th. “After a comprehensive search process, we are thrilled to appoint Ralf Roth as CEO. Ralf brings strong leadership and experience with machine learning and cloud computing that will help us scale and expand on the innovation that defines QB in the market,” said Christian Hauff, Co-Founder and outgoing CEO of Quantitative Brokers. Hauff will continue on as a member of QB’s Board and Executive Committee and will oversee the firm’s client and industry relationships. “Ralf is very well placed to succeed me in the role of CEO and I look forward to as… 2017-12-08 00:00:00 http://www.bobsguide.com/guide/news/2017/Dec/8/quantitative-brokers-appoints-ralf-roth-as-ceo/

Google’s AI teaches itself chess in 4 hours, then convincingly defeats Stockfish

…There has just been a revolutionary development in the world of AI, and in the world of chess. Google’s Artificial Intelligence project, DeepMind explains they’re on a scientific mission to push the boundaries of AI, developing programs that can learn to solve any complex problem without needing to be taught how. A little over a year ago, DeepMind released AlphaGo, which sensationally defeated the world champion of the famously CPU unfriendly ancient Chinese game, GO. Now their AlphaZero program has kicked up a storm in … 2017-12-09 17:16:47+00:00 http://trove42.com/google-ai-teaches-itself-chess-defeats-stockfish/ CloudQuant Thoughts: Why does everyone want to play chess with AI and Machine Learning? We want to see some Machine Learning project team take on Settler Of Catan!

CityBldr raises cash, prepares to expand to California with software that reveals hidden real estate value – GeekWire

…icer at Touchstone earlier this year. Initially, CityBldr was focused on residential properties but now has expanded its service to cover nearly all types of real estate. “What we’ve learned is our machine learning algorithm doesn’t care if its a house, or an apartment, or a gas station, or a vacant parcel of land, or a commercial building, or an office building … it doesn’t care at all,” Copley said. “It just sees that there’s opportunity in that land and it predicts the highest and best use of that land.” CityBldr is hoping to hire a team of about seven in Los Angeles and bring on an additional 15 to 20 … 2017-12-07 23:47:18+00:00 https://www.geekwire.com/2017/citybldr-raises-cash-prepares-expand-software-reveals-hidden-real-estate-value-california/ CloudQuant Thoughts: In Chicago, there is the unused old post office. The building is huge and spans a highway that most people in the western suburbs use. We wonder what CityBldr would recommend to the Chicago mayor about this building?
Morgan Slade, Python Data Scientist and Trader

QuantNews Interview with CEO Morgan Slade

With over 20 years of experience as a trader, portfolio manager, executive, and entrepreneur, Morgan Slade is now the CEO of CloudQuant, a cloud based quantitative strategy incubator and systematic investment fund. He has built quantitative trading businesses at some of the world’s largest hedge funds and Investment Banks …
Open, Close, High, Low

Share Ordering Demo using Market, Limit, and Midpoint Peg Orders

The CloudQuantAI github repository holds the share_ordering_demo tutorial/code that demonstrates ways to buy and sell stocks in the CloudQuant backtesting engine using Market, Limit, and Midpoint Peg Order types. There is no single “right way” to do any of these. You will have to think carefully about your algorithm, how it determines when to buy and sell, how large a trade you want to implement, and how quickly you need your orders filled. To give an example, let’s imagine a hypothetical stock XYZ, at time t0 with bid prices at 29.95 and ask prices at 30.05.

Market Orders

One option is a simple market order: order_id = order.algo_buy(self.symbol, algorithm=”market”, intent=”init”, order_quantity=num_shares) This means that your order will fill at the lowest price someone is actively willing to sell it at. In real trading, you would never buy significant shares of stocks like this, because people will raise their ask price when they realize someone is buying large volumes on market. In backtesting, however, it is essentially assuming you are buying at the ask price for that time, which is reasonable. Your order will always fill immediately, and the only risk is that if the stock price shoots up, you will be paying whatever price the stock goes up to. In our example of stock XYZ, you are buying at 30.05 at t0, though if your order is placed at t0, you may be purchased at the ask price at time t1, which could be different from the ask at t0. Market orders will simply purchase at whatever that ask price is.

Limit Orders

Another way is to initiate a limit order, based on the ask price: order_id = order.algo_buy(self.symbol, algorithm=”limit”, price=md[self.symbol].L1.ask-.01, intent=”init”, order_quantity=num_shares) or order_id = order.algo_buy(self.symbol, algorithm=”limit”, price=md[self.symbol].L1.ask*.99, intent=”init”, order_quantity=num_shares) These two algorithms place an order for a stock with a limit on the price. In the first case, we set a limit one cent below the ask, and in the second our limit is 99% of the ask price. These are likely to get filled, but not guaranteed, though they will get a better deal than a simple market order. The farther below ask you go, the better a deal you might get, but the higher a chance that you won’t get filled. The lowest you can go is probably 95% ask or 5 cents less than the ask. If it’s important that you get your order filled immediately, you will want to place a more aggressive limit, such as the ask price PLUS 5 cents or 105% the ask price. This is similar to a market order but will keep a lid on how much you actually will pay for the shares. This is a critical distinction in live trading, but less important in back-testing. In our example of stock XYZ, if we, at t0, place a limit order one cent below the ask, we are essentially offering at t1 a price of 30.04. Cloudquants backtesting environment does its best to approximate whether someone would have been likely to meet our price limit or not. If the price of stock XYZ moved up at t1, there is a very high chance we would not have been filled. If, however, we set a limit of ask + 5c, we would have placed a limit at $30.10, and we would have likely been filled unless the stock shot up more than that.

Midpoint Peg Orders

Finally, we have a slightly more complex way of computing our trade price, using a “midpoint peg.” This algorithm is only available in the elite version. order_id = order.algo_buy(self.symbol, algorithm=lime_midpoint_limit_buy, price=md[self.symbol].L1.ask*1.05, intent=”init”, order_quantity=num_shares) order_id = order.algo_buy(self.symbol, algorithm=lime_midpoint_limit_buy, price=md[self.symbol].L1.ask+.05, intent=”init”, order_quantity=num_shares) You will also, earlier in the code, need the lines: lime_midpoint_limit_buy = “4e69745f-5410-446c-9f46-95ec77050aa5” lime_midpoint_limit_sell = “23d56e4a-ca4e-47d0-bf60-7d07da2038b7” Though the exact algorithm is only available in the Elite CloudQuant version, you could approximate it in lite by using the mean of the ask and bid prices. This is similar to what the “Lime” midpoint peg does, but the real version should include elements such as the volume of the shares to more accurately estimate where the price would have been. If your trade doesn’t need to urgently fill, the lime midpoint peg is a good way to go, however, if your trade requires an immediate fill, this may give you unrealistic purchase prices, and make your algorithm seem better than it really is. In our XYZ example, this essentially assumes we would always be purchasing shares of XYZ for $30.00 at t0, and then the average between bid and ask at t1, and so on. The public scripts with these examples are available for your copy and re-use.