Algo Testing for MiFID II

Ideal Prediction has developed a suite of tools for monitoring algo behavior, to meet MiFID II requirements for rigorous algo testing. Send a note to if you would like to see a demo.

There are a few solution providers in this space, but at first glance, they appear to lack domain expertise with FICC products. 

Profit & Loss magazine interviews CEO John Crouch

In February, Profit & Loss reported that GTX had partnered with Ideal Prediction, an independent trading analytics and data science company, to offer its clients analytics aimed at optimising their FX trading. GTX first hired Ideal Prediction to optimise client liquidity pools and trade execution performance in March 2016 and the perceived success of this project, combined with the management teams’ strong working relationship with Ideal Prediction CEO, John Crouch, from his time working at Credit Suisse, prompted the two firms to look for more ways to utilise the data at GTX’s disposal to help its clients. The end product of this was the analytics tool that GTX began offering to firms in February.

Read More

PRESS RELEASE: GTX and Ideal Prediction to Provide TCA, Advanced Execution Analytics to Clients

Liquidity Management, Strategy and Algorithmic Optimization, Transaction Cost Analysis to Improve Execution Performance and Risk Management for Buy and Sell-Side Market Participants

NEW YORK, 13 February 2017 -- GTX, the institutional foreign exchange (FX) arm of GAIN Capital Holdings Inc., and Ideal Prediction, an independent trading analytics and data science company, are offering clients FX data and advanced analytics to optimize their FX trading.
The market data, tools, and services enable buy-side and sell-side market participants to optimize profitability and simulate strategies as well as perform Transaction Cost Analysis (TCA). The new offerings further enable sell-side market participants to benchmark execution performance, analyze client flows, and optimize risk management strategies.
The analytics are powered by GTX’s rigorously maintained, fully anonymized, and aggregated tick data sets derived from programmatic liquidity and buy-side order flow on its FX ECN.
GTX hired Ideal Prediction to optimize client liquidity pools and trade execution performance in March 2016. The project’s success prompted the two firms to evolve the analytics for both the buy and sell sides.
GTX launched GTX Data Sciences in December 2016 to formally offer the analytics to its clients.
“The power and applications of Ideal Prediction’s robust, flexible analytics are clear to market participants, who are using them to improve their FX trading strategies and processes,” said Steve Reilly, Managing Director and Global Head of Liquidity, GTX. “From day one, Ideal Prediction’s tools gave us a deeper, more nuanced view of the complex dynamics within our ECN and we are excited to extend these benefits to clients.”
In addition to collaborating with GTX, Ideal Prediction provides data, analytics, and services to fixed income, currencies, and commodities (FICC) market participants. These analytics are provided through Ideal Prediction’s innovative Measurement as a Service (MaaS) platform and powered by real-time, anonymized, and derived FX market data from GTX’s FX ECN.
“GTX’s liquidity optimization team works in deep collaboration with its clients. Enabling them with a powerful set of market data and independent analytics was a natural next step.” said John Crouch, Founder and CEO of Ideal Prediction. “Our partnership will empower GTX and its clients to achieve each client’s self-defined goals. We look forward to helping GTX, GTX’s clients, and the overall market.” 
About Ideal Prediction
Ideal Prediction creates value by optimizing client revenue and leveraging the firm’s data analytics and trading experience. Ideal Prediction provides turn-key analytics and tick data in addition to bespoke consulting.

Additional information at

About GTX
GTX operates electronic trading venues and provides agency execution and clearing services for buy and sell-side institutional FX market participants.

GTX provides an array of electronic and voice trading solutions through its various entities including an ECN, prime services, a Swap Execution Facility for NDF trading, and a Registered Swap Dealer, which facilitates trade executions on an agency basis. Clients include banks, hedge funds, CTAs, fund managers, proprietary traders, brokers, and algorithmic trading firms. 

Additional information at

About GAIN Capital
GAIN Capital (NYSE: GCAP) provides market access and trade execution services to a diverse client base of retail and institutional investors across a range of exchange-traded and OTC markets. Founded in 1999, the company today supports customers in over 180 countries via several globally recognized brands, including, City Index and GTX.

GAIN Capital is headquartered in Bedminster, New Jersey, with a global presence across North America, Europe and the Asia Pacific regions.  

For more company information, visit

DataEngConf NYC - Tying It All Together

DataEngConf NYC - Tying It All Together

From Jason at Ideal Prediction!

DataEngConf had its first NY conference this fall with the goal of bringing Data Engineers and Data Scientists together. There wasn’t a unifying theme or tagline, but the ideas that kept coming up to me were

  1. Making it easier for data to be exchanged and analyzed and

  2. Broadening the use cases for tools that were originally built around specific niches.

As a team that works with both R and Pandas and with clients that use one or both, interoperability is huge for us. In particular, we’re really excited about the Apache Arrow project, which aims to be a high performance interface. In creating intermediate files in the data pipeline that need to be passed to different platforms or languages, around 80% of our run time has been spent on reading/writing CSVs.

Apache Arrow aims to cut the serialization/deserialization process out of the flow, which could, with no other changes in our code, allow us to speed up data transformation roughly 4x. While Apache Arrow is still a ways away from being broadly implemented, R and Pandas have already worked on an alpha implementation for use between the two called Feather.

Other things we were excited to see:

  • The Hadoop ecosystem seems increasingly focused on ingesting messier and more varied data sources
  • Kafka has built a third client called Kafka Streams, which offers a set of lightweight libraries aimed at augmenting the capabilities of the simpler basic producer and consumer client paradigm without the much more complex architectures of Spark or Storm

On a less technical note, the idea of making data and data exploration more accessible to everyone was pervasive at the conference. Several Data Engineers mentioned in their talks that one of their goals was to not only make it easier for Data Scientists to run more complex experiments and iterate faster, but to allow people in roles not traditionally considered Data Science to explore the data and feel empowered to form insights on their own. We can’t agree more -- making data easy to explore and interact with is one of our core focuses here at Ideal Prediction.