Patented Solutions

Contact Us: 1 (617) - 237 - 6111

P.O. Box 181, Weymouth, MA 02191 Email: info@databoiler.com

Patented solutions that crossover between music and trade provide more accurate detection of onset signals / trade irregularities at accelerated speed and more tolerable to unsynchronized clocks/ timestamp issues + more. • The ONLY solution to address IOSCO - CR12/2012 challenges to effective market surveillance • Machine learning, ontology to enable algos development and discovery of unknowns without the expensive and hard-to-learn tools • Time-lock cryptography to make market data available securely in synchronized time Applicable to all trading desks, cross-asset classes, and markets

Our patented solution reduces data storage and boosts the efficiency in data distribution, while also enabling the replicate the depth-of-book information (relative strengths in bid/ask price and steepness of the price curve). We acknowledge that the buy-side also wants the SIP to include all the odd-lot details amid some hidden cost for high priced stocks. Our response is: When we are in the midst of systemic reform, asking for too much or insisting on “complete” transparency, may indeed be detrimental to price discovery and the sustainable development of a healthy market. We do want to strike the appropriate balance to avoid a “No fish can survive when the water is too clear” situation. Given that, we’ll preserve the richness of contents the best we can, while making the tools fast, easy, secure, and fit for the effective monitoring of trade activities.

MP3 is indeed a lossy compression type, while human ears cannot distinguish almost any difference from lossless music. Lossy methods yield a substantially greater compression ratio (60% or more of the original stream) as compared to traditional techniques (only 5-20%) that exploit statistical redundancy, Huffman coding, or probability method to represent and compress market data.

Since a thousand trades can occur between 50 +/- milliseconds, the inexactitude in trade sequencing would cause analytic results based on vector measurements/ visualized heat-maps to be erroneous. To overcome this inherent problem of data imprecision, our suite of patented inventions applies a “music plagiarism detection” method to achieve higher tolerance to the unsynchronized clock issue and is capable of recognizing patterns more quickly (up to 50 milliseconds top speed, as compared to taking hours or days or even months for trade review). Aside from the accelerated speed to decipher what’s going on in the market, it has fewer false-positives/ false-negatives than the traditional techniques. It makes implementation of preventive controls in real- time possible; and there are other benefits such as the ease of trade reconstruction, order book replay simulation, backstop assurance, case management capabilities, crowd computing methods, and more.

Big Data | Big Picture Everybody talks about market problems or regulatory burden, but not just anyone can come up with a suite of patented solutions to make the best of every situation. Marvel at our ability to solve the industry’s thoughest challenges. It is about: the industry nuances, market design and economics, as well as the enabling technologies to make a positive difference.

Context of the Problem

Neural network Deep Learning • Very slow to train, drains resources • Take forever to generate results • Often too late to help in a situation • Cannot handle different input types • Need scaling inputs, Needs tuning • Does not provide probability estimates • Lack of good interpretability (BLACK BOX) • Assume centralized intelligence knows what’s going on better than those in the field Random Forest (Decision Trees) • Fast to train and score • Trivially parallel • Require less tuning • Probabilistic output • Can adjust threshold • Good predictive power Ontology / Genres to address scalability issue, making it suitable for large scale complex deployment. KNN • Robust to missing data • Robust to outliers • Good predictive power Centralized - one size fits all Decentralized - Field Intelligence

Different Learning Models

Emphasis on the Hierarchy of Tree rather than the Tree Structure Top and Bottom Voice Representation with Propagation FIG. 9 FIG. 3 Address contextual issues such as Market Volatility US Patent No. 10672075 Canada Patent No. 3,135,792 p ending in other International regions Temporal, Polyphonic  Any single ‘trigger’ may not be a violation. However, the legitimacy of trade activities may be challenged if they occur in an order resembling a set of triggers in the lessons database.

DEMO

• Aggregate and Decompose • Propagation to roll - up or drill - down the dimension Overall Market  Ticker and/or Broker level  Trading Desk Drag and drop to roll - up or drill - down the dimension Trading desk - lowest dimension Overall Market according to chosen criteria Query criteria Solo / Stereo Buy (Bid ) Sell (Ask) No/ low - code aggregate/ decompose data across markets/ asset classes Tune Control Panel • Depth - of - Book • Trading Venues • Shadow Banking • Obfuscation Lessons • Instruments • Triggers • Patterns • Genres E asier to equip Traders / Risk & Control Experts with “what you see is what you get” tools to enable them to become Quants than vice - versa

Dectection Engine

Scrutinize instrument, trader, trigger, pattern, reconfigure workflows, customize scores, etc . Basic Controls Orders Stream Detection Engine Backstop Assurance Parameters • Pattern Recognition • Model and logics Scorer Flag: trade Irregularities • Synthetically created trades • Aggregate risk, material exposure • How quickly untreated cases become possible threats Compliance Dashboard Algorithms Crowd Quickly & fast + Field knowledge Mass customization, F lexible implementation Macro oversight to apply policy limits, Best practices s haring +

Time-lock encryption is a method to encrypt data such that it can only be decrypted after a certain deadline has passed. The goal is to protect data from being decrypted prematurely. There are various ways to build time-lock encryption for different protection requirements. The architecture needs precise calibration of time with an independent time aware atomic clock, such as the NIST. Besides, we don’t want to push the bottleneck to an arms-race of using high-performing computers to decrypt data. Hence, computational resources and the type of data content must also be considered in the design of a reliable encryption scheme.