The all-in-one platform forProfessional Algorithmic Trading

Ogre Robot is both a realistic, Faster Than Real-Time validation environment and a nearly zero-maintenance, 100% automated operation platform for Trading Algorithms modeled to the regulated stock market.

Risk Management

All successful trading algorithms eventually face hard times. Without Risk Management, drawdowns are experienced on their plenitude. Ogre Robot provides a solid risk management infrastructure able to allow, deny or force the apropriate investment behavior.

More...

Maturation / Operation

Learning & Intelligent Model mimicking is an ongoing process which, on one side, needs data from the book of orders; on the other, specially crafted infrastructural software allows processing and data gathering in real-time as well as a 100% automated operation.

Other Features...

How to Start

Apart from all that has been said, HFT modelers usually focus their energy on their algorithms and struggle to operate them. Ogre Robot was designed from scratch to partner with those modelers and allow a 100% automated operation in the cloud or on-premises.

Get In Touch

Exchange Simulators & Gateways

Ogre Robot supports new Exchanges in two modes: simulation and operation. For the operation, we just need a communication module (Direct Market Access) between the two platforms; for the simulation, an implementation of the exchange itself is developed, respecting all the rules, protocols, limits, regulation requisites and so on. New exchanges are added as new partnerships demand it. Here is our current list:

B3's Puma Stock & Derivatives Exchange Platform, São Paulo, Brazil

B3

B3 Stock Exchange, São Paulo, Brazil
London's Millennium Exchange Platform, London, United Kingdom

London Stock Exchange

London Stock Exchange, United Kingdom

Please, Contact Us if you have any inquiry about Exchange Integration.

Risk Management

When submitted to real & realistic scenarios, each trading algorithm will have it’s own performance characteristics, which can be quantified as the probability it will win or lose each cent on all foreseen scenarios for a given holding time. Together, they form the Algorithm’s Risk Factor matrix. We shall only engage in operations with the best risk factors, unless a target ROI had been set which obligates more operations to take place in order to achieve the goal: in this case we have to engage in riskier operations, updating the Algorithm’s Risk Factor matrix on the fly. If the Risk Limit Factor and ROI Risk are unsolvable with the current algorithm characteristics, the Risk Manager will deem the operation impossible and halt it. This is an example of a Goal Oriented Risk Management Strategy, suitable to work with one of our Fast Trading Algorithms, both on simulation and operation modes.

Our Risk Management strategies, together with our Real-Time Performance Monitoring technologies are responsible for not letting any potential losses scale up – On speculative trading algorithms, this may happen really fast. A rock solid cooperation between these subsystems is key for our sane 100% automated Algo Trading operation.

Icon indicating that the Ogre Robot operation is automatically shutdown uppon risky scenarios, to prevent revenue loss.

Shutdown MechanismsOperation automatically shuts off on adverse performance.

When using our Goal Oriented Risk Manager, the Ogre Robot platform is able to predict on which scenarios a given Trading Algorithm is able to achieve that goal or not, as well as informing the probability for each scenario happening, one after another. The pre-rendered scenario sequences may cover the whole day or just the next minutes, depending on the market behavior. Human input may restrict further were to stop issueing orders, based on the predictability window and the maximum hold time an asset may have in order to fulfill the goal.

Icon representing the relation between the Trading Algorithm model, the ROI target and the market bahavior.

Model & Goal Oriented Risk Manager & MarketWill the relation between these 3 entities issue orders?

Many automated models trade nowadays. Speed helped us here: about predictability, our fast platform allows us to migrate a little further from the realm of probabilities to the realm of certainty. Ogre Robot has a built in Automatic Risk Manager which uses Computational Intelligence Technologies and is able to come up with on-the-fly strategies, both on simulation and operation times.

Icon representing the relation between the HFT Algorithm model, the ROI target and the Risk Management strategy.

Goal Oriented vs. ConservativeDo we really have to choose?

API available to models

When you partner with us, your trading model will be implemented by you or by us, and will have a number of useful information as well as order commands promptly available.

Triggers

Identifying interesting events is as simple as setting triggers on conditions. E.g.: SET_TRIGGER(<method>, <condition>)For instance, we may wakeup routine SELL1 when the ‘ask’ of security 1 is rising for the last 5 successful transactions, it is greater than security 2’s ‘ask’ and the ‘bid’ for security 3 is dropping for, at least, 5 consecutive transactions.

Decision Making

Usually, after a wake up the algorithm is able to use more complex operations in order to check if the pretended action (SELL1 in the previous example) should really sell security 1 – like determining a possible bid for it. This involves a process of decision making and it may be done without fear: in case of a certain number of adverse operations (yielding revenue loss), the Risk Manager in charge will stop the operation. The routine may, then, be reprogrammed with the ease of log files, scenario dumps, etc. The same rules apply whether in simulation or real operation mode.

Playbacks

Implemented Models may be as elaborated as C, C++, Java or Python languages allow. For those who need customized training, we have a bunch of APIs to feed the algorithm with real old data – Order Book, Trade Book, … If present, the algorithm’s custom training method will coordinate the process and may require any number of replays (simulating real-time, but actually taking place faster than real-time), may set signal matrices (useful for neural networks) and command new training processes to start in parallel with different settings, in the search for the optimum values – or simply use our built-in Genetic Algorithm.

Automated Monitoring Extensions

Ogre Robot platform is very modular. This means the built in monitoring facility may be extended to watch on whatever data your algorithm produces or rely on and issue warnings, trigger the safe mode and use any of the API methods. The monitoring may be running on the same machine as the operation or be set remotely, analyzing independent data, for an extra level of protection.

Algorithms

One of the Ogre Robot strengths is its realistic simulation environment. For that, we have to implement real Algorithms used in Algorithmic Trading as well as algorithms that simulates human operators, using several different strategies. Here are some classes of algorithms we use:

Icon representing the future prediction abilities of the data mining algorithms

Data Mining

The Observers

These algorithms explore patterns, cycles, corelations and other predictable behavior infered from observing market raw data. They may implement human knowledge or use computational intelligence to find such patterns. There are many possible patterns and many possible ways of detecting them, therefore there are several algorithms, ranging from high to low recurrence.

Icon representing the huge speed of high frequency trading

High Frequency Trading Algorithms

Large Investment Banks

These algorithms aim to make gains at the milli or even micro second range, hence the term High Frequency. They are the messy warriors big financial institutions build to gladiate one another, providing liquidity and consistent related securities prices as a side effect. They need to be fast, so they are not very smart. Usually they follow very simple rules and are co-located at the same data center as the stock exchange, since every µs counts on their race.

Icon representing the herd behaviour

Model-Based

From theory to practice

Market behaviour that may be represented by mathematical or statistical models are often borned in theory and later validated in practice. They form the model-based class of algorithms. Many of them are possibilities that either cannot be observed or are valid only on specific market conditions.

Partnership

If you want to discuss partnership or have any doubts, please, contact us using the form below

This small FAQ may dismiss some doubts:

No. Ogre Robot was built to adopted by a whole company who needs to optimize their professional computer & financial engineering tools regarding automated algorithmic trading. It doesn’t mean we are closed to partnerships with individuals, tough. Just keep in mind it wasn’t designed for the home trader and that are better tools for this task.
Ogre Robot’s main goal is to offer a nearly 100% automated solution with a rock solid risk management. Don’t get us wrong: automated doesn’t mean unassisted. By automated we mean you don’t need to manually approve every investment decision, but you should always be around, inspecting and studying the results. Pressing the stop button will hardly be needed, but constant evolving and checking if the model is still valid is the work to be done.
We work in two ways:We share the framework with you (including the source codes) and you share your investment model with us. We implement your model using our tools, so you don’t need to know the internals of Ogre Robot if you don’t want.We sell you the right to use our framework. No source codes or models are shared and you must learn how to code your trading algorithms using our faundations.
As long as we have access to the exchange’s integration documentation, we will develop the integration module for free. Remember that you need a valid account within the exchange in order to have access to the DMA feed as well as to issue orders.