Biography

Nick started his PhD study at the University of Surrey since 2010. His principal supervisor at Surrey is Prof Paul Krause and his co-supervisor is Prof Yaochu Jin.

He founded Neural Technologies Limited (see www.neuralt.com) in 1987 and then as Chief Executive he achieved a range of firsts using neural computing technology – both hardware and software:

• Design and production of the world's first neural integrated circuit working with Micro Devices in Florida and design and production of Europe's first neural-chip for Smiths Industries.
• Chosen as the principal technical advisor to the UK Government £6m Neural Technology Transfer Program that was completed in 1997.
• Worked with NASA and Government projects, ranging from speech recognition, anti-fraud systems, signal and image processing, to customer loyalty, churn and data analysis.
• As CEO, Nick positioned Neural Technologies as a leading player in fraud management and credit risk. He developed a proprietary neural computing system the Advanced Modular Adaptive Network (AMAN) used in all the firms products.
• Today, Neural Technologies solutions scrutinise billions of transactions every day in real-time and provide protection for 1-in-7 of the world's mobile telephone subscribers from fraudsters.

Nick stepped down as CEO in September 2000 and then formed his own consultancy firm.  Nick is respected for his work in reducing crime using risk and anti-fraud technologies through AI. Nick also remains a skilled software engineer at heart – languages include C, C++, C#, Java etc., and continues to develop software today. In his spare time, he preserves both hardware and software artefacts of “antique” British microcomputers dating from late 1970s and has a growing collection.

Major Achievements

• Self-started own technology company as an inventor and entrepreneur and grew this to over 65 staff.
• Worked with a range of UK and international Universities on neural computing and advanced technology, teaching courses, lectures, teaching aids and guidelines, setting course material for more than 17 years.
• Appointed UK Government spokesperson on for promoting awareness of neural computing for four years.  Produced Government Best Practice Guidelines with Aston University.
• Widely published technology papers and articles.  Received awards from IEEE and NASA.
• Created the Advanced Modular Adaptive Network as the fraud detection engine used in the company’s products and services for fraud and risk management.
• Opened offices in Singapore, Sydney and New York – including working with local research Universities, local press awareness, legal agreements, employee contracts, reporting, accounting, etc.
• Raised millions in private capital investment and managed London city flotation process – including legal due diligence and accounting.
• Formed consultancy firm – helping firms raise finance, non-executive director/right-hand-man, technical advice and software development, contracts, hands-on help and assistance, executive coaching, workshops, etc.
• Remains up to date with current technology and software engineering methodology. Including AI/Neural Computing. Proficient in Microsoft NET, C#, C++, Perl, JAVA, SQL, etc.  Detailed knowledge of Windows,  Linux, Microsoft Office, Web design, databases (ORACLE, Access, etc.), networking, electronic design and build, project management and QA.

Experience

• 2010, Thoughtified Limited – Business Development Director, Guildford
  Founded in 2009, Thoughtified Limited is an award winning firm recognised as a leading authority in the application and development of agile software products based in the real-world using large datasets; providing innovative design, build and deploy services.  
  Thoughtified Limited was formed out of the University of Surrey, Department of Computing, which has for many years been involved in the research and development of distributed and intelligent systems, shaping them to the demands of industry problems.  In particular, the department's Nature Inspired Computing and Engineering (NICE) group develop computational models and algorithms inspired from natural intelligence found in physical, chemical, social and biological systems.  One such approach is the advanced use of neural computing for pattern recognition and classification (See http://www.thoughtified.com/).  
• 2010, Public Square – Innovations Director, Dorking
  Publicsquare Limited is an interdisciplinary, creative research consultancy, founded in 2002. Publicsquare focuses on the research and development of digital strategies, prototypes and products; employing user-led, intelligent systems and new approaches to creative innovation for commercial-service, public sector, and peer-to-peer use (see http://www.wesaywepay.com/).
• 2005 – 2007, Hasmodia Limited – Technical Director (p/t),  Dorking
  Joined BAFTA nominated Hasmodia Limited (see http://www.hasmodia.net/) as Technical Director to provide input and direction on a range of advanced multi-media projects – where the traditional models for television are becoming blurred with the greater range of delivery mechanisms available and higher audience expectation for interactivity.
• 2001 – 2007, MindsI Technology Limited – Managing Director,  Havant
  Founded MindsI  as a consultancy company that provides advice to local technology companies:
  • Technology planning, software and hardware development, project management and strategy.
  • Developing management practices and procedures – including advice on company law, director responsibilities, solvency, company formation, accountancy, employee contracts, terms & conditions of sales, etc.
  • Running hands-on workshops to help business people understand the role of technology.
  • Fund raising – loans and equity.
  • Innovation, technology reviews, due diligence reports for investors, patent reviews.
• 1994 – 2000, Neural Technologies Limited – Chief Executive Officer, Petersfield/New York
  As CEO, positioned the firm to be a leading player in the credit risk scoring and fraud management industry (see http://www.neuralt.com/).  Neural offered two main software products that were based on a proprietary neural computing system created by myself called AMAN.  Nick was responsible for:
  • Finance (accounting, reporting, planning, working with tight cashflow)
  • Commercial (team recruitment, marketing, planning, revenue growth, licensing, contract negotiation)
  • Legal and business affairs (agreements, due diligence, governance)
  • Strategic planning (market research, overseas, partnerships)
  • Technical (research and development, innovation, support, products)
  • In early period, worked with NASA and Government projects, ranging from speech recognition, anti-fraud systems, signal and image processing, to customer loyalty, churn and data analysis.  Focused Company into two market sectors and completed the development of off-the-shelf products.
  • In-house staff training and training programme.  Working with Universities and local colleges.
  • Grew revenues by an average 40% per year
  • Substantially enlarged the base of clients through branding and extended penetration within existing clients' organisations and creative contract negotiation
  • Won Government innovation grant awards to create a customer profiling system with advanced visualisation
  • Changed business from consultancy to repetitive licensed software products and focused Company into two market sectors.  Produced licence agreements to protect repetitive revenue streams.
  • Completed development of new products and launched these in 1997.  Personal order-wins include JP Morgan, Lloyds Bank, Standard & Poor's, Nationwide, Bradford & Bingley, British Gas, Orange, etc.  Negotiated at Board level and created both service and product legal agreements.
  • Set up worldwide strategic partnership agreements with IBM, CSC, Grupo Concepto Venta (Mexico), Lynx Financial (South Africa, Australia), Midas-Kapiti and Ernst & Young.
  • Delivered full Y2K compliance to the business
  • Raised capital from private investors (UK and overseas) as well as VCs.  Initiated IPO, including locating broker, lawyers, accountants, due diligence process and “city” management team.
  • Regular Chairman and speaker at many events.  Invited after-dinner speaker.  Good relationships with all media, TV and Radio.  Excellent corporate PR - required for city/shareholder and customer confidence.  Presented regular Radio 4 and 5 shows.
• 1987 – 1994, Neural Technologies Limited – Technical Director, Petersfield
  Founded Neural to exploit emerging neural computing technology in industry.  During this period, worked as fee-based consultants with a number of major blue-chip organisations on a variety of projects.  Nick used this period as the springboard for the future products:
  • Project management for development of hardware and software solutions for customers – including formal procedures and quality control, documentation and agreements
  • Presentations to prospects and customers, promotion of the technology and education to the market
  • Design and production of the world's first neural integrated circuit working with Micro Devices in Florida and design and production of Europe's first neural-chip for Smiths Industries
  • Working with major UK and overseas universities and research groups.  Ran various workshops and seminars and a Teaching Company Scheme.
  • In 1993, chosen as the principal technical advisor to the DTI £6m Neural Technology Transfer Program that was completed in 1997 to personal Ministerial acclaim.
• 1986 – 1987, Wayne Kerr (ATE) plc – New Product Development, Manager, West Sussex
  WKR was one of the key companies producing Automatic Test Equipment.  Nick reported to the Technical Director and was responsible for developing a new range of products - it was an industry breakthrough and the company was able to float in 1987 on the back of the commercial success.
• 1985 – 1986, IGG/K-Bytes Limited – Senior Software Engineer, Cosham
  K-Bytes was a software house and Nick worked on a range of software projects for their clients, including the development of low-level code for Apple, operating system and Point-of-Sale software.  Other projects included working with Marks & Spencer using Teletext to download pricing, London Stock Exchange and the European Space Agency.
• 1984 – 1985, NCA Limited – Software Engineer, Winchester
  The company had developed its own range of desktop computers and was one of the first UK firms to provide a full low-cost office network.  Nick worked as a software engineer from low-level hard disk and network drivers to user interface and modem software.

Earlier

• Developed a rack based computer and marketed it
• Wrote computer games for Atari Corporation in USA
• Worked as a sub-contractor to Sinclair Research (Sir Clive Sinclair) on the operating software in the ZX-Spectrum ROM and on one of the first 16-bit personal computers called the QL.
• Founder member of the Southampton University Amateur Computer Club.
• Wrote articles for magazines such as Personal Computer World and Practical Computing.

Research Interests

• Using neural computing and adaptive techniques in the detection of emerging, real-time patterns in a high volume transactional environment
• “Sea of Data” visualisation techniques to aid in the development of rules, models and “global” view
• Automatic learning methodologies to create models for the detection of anomalous events and the automatic extraction of “rules” from models
• Presetting a neural network with fixed rules and parameters for known patterns and then automatically updating these during learning from on-line activities and presenting these changes to an operator (emerging classes)
• Real-time deployment of complex neural hybrid systems in a mission-critical environment – including verification of models
• Building timed events into a neural network architecture
• Hybrid neural symbolic processing for the easy interpretation and knowledge extraction in real time, financial transaction environments, with robust fault-tolerant learning on in-complete or “noisy” data-feeds.

Research Collaborations

IEEE Fraud Detection Task Force: http://www.moyo.me.uk/fraud/fraud.html

Publications

Fraud and Risk

• Detection of Unusual Trading Behaviour and Fraud on the Trading Floor using Anomaly Detection
• Prediction of FX US$ rates using Neural Networks
• Scoring of Individuals for Automotive Loans to reduce Bad Debt
• Loan Scorecard Development System and deployment server
• Credit Card Application Fraud Detection
• Commercial Company Ratings using Bayesian Networks
• Detection of fixed-line telecoms fraud – Real-time Analysis of 30 Million+ Call Records a Day
• Detection of mobile-telecoms fraud - real-time, high-volume

Database Mining

• Identification of Customers Unlikely to Renew their Motor Breakdown Insurance using Neural Modelling
• Prediction of High-Spending Customers and their Product Types in Catalogue Company using Neural Data Mining
• Identification of Electricity Users to Predict Demand for Forward Purchasing of Electricity
•  Account Early Warning Loss System - Identification of Defecting Photocopier Customers using Neural Data Mining
•  Use of Neural Networks to Predict Food Texture (baking)
•  Using Neural Computing for the Development of a Best Branch Location Prediction System
•  Early Detection of Wireless Telecom Subscribers Likely to Churn
•  Early Prediction of Wireless Base-station Failure in Large UK Cellular Network using Neural Anomaly Detection
•  Streamlining Litigation Procedures – Assessing the most cost-effective targets for litigation

Image Processing

•  Vehicle Identification System for Toll Auto-pay (VISTA) - automated vision recognition system for locating and reading vehicle registration plates
•  Blood Speckle Tracking (ultrasound scanner) using Neural Image Processing to Calculate Velocity and Angle of Movement of individual Blood Cells to aid in the Diagnosis of Breast Cancer
•  Image Processing and Neural Computing in Diabetic Retinopathy Screening - the automated identification and diagnosis of hard and soft retinal exudates
• Pizza Manufacturing Quality Control – Neural Image Processing
• Quality Control in Manufacturing of Automotive Gear Box Assemblies using Laser Scanner and Neural Image Processing
• Use of Neural Networks to Recognise Blemishes on Food Products
• The Use of Neural Networks to Recognise Advertising Logos on Live Television Pictures
• Image Processing system to Recognise Blemishes on Contact Lenses
• PictureNet System – Neural hand-drawn picture recognition system – Interactive Neural Demonstrator based on Pictionary game

Digital Signal Processing

• Oil Pipe Corrosion Detection – using non-intrusive sensors and neural signal processing
• Beer Barrel Leak Detection using Image Processing
• Classification of Inductance Profiles Derived from Coin Vending Machines using Neural SOM Techniques with Low False-Positives
• Whisky Blending Analysis using a Novel Polymer Sensor and Neural DSP Processing
• Final Automatic Testing of DC Motors using Neural Digital Signal Processing
• Implementation of Hardware Parallel Processing System (16 Processors) for Real-Time Signal Analysis and Recognition
• Implementation of a VMEbus  Based Image Processing Card with Neural Processor
• Speech Recognition system using HMM  and Neural Networks to give Superior Speaker Independent Word Recognition in Noisy Environments

 Optimisation

• Ambulance Scheduling System – optimise the choice of patients to vehicles to individual journeys, to arrive at the destination within time with no journey of over an hour, minimising “down-time” of each vehicle
• Optimising Delivery of Perishable Plants and Flowers from Supplier/Depot to Shop – using Neural Combinatorial Optimisation (TSP ) Ring Network
• SX-EW Process Optimisation for Copper Extraction

Robotics and Control

• Robot Control of Electric Wheelchair for Severely Disabled Persons Using Neural Computing and Fuzzy Logic for Navigation and User Input
• Application of Neural Networks for Adaptive Remote Vehicle control : the stair climbing problem

Data Visualisation

• Locating Gold Ore Deposits in South Africa Using Neural Data Fusion and Anomaly Detection
• Neural Computing and Virtual Reality Interactive Environment for Visualisation of Large Corporate Databases

• VERSAmodule Eurocard bus – a hardware bus standard.
• Hidden Markov model (HMM) – a statistical model based on a Bayesian network.
• Travelling Salesman Problem (TSP) – “Given a number of cities and the costs of travelling from any city to any other city, what is the cheapest round-trip route that visits each city exactly once and then returns to the starting city?”.

(1992), Ryman-Tubb, N., “Designing an Electronic Wine-Taster using Neural Networks”.  Electronic Engineering, Vol. 64, No. 783, p. 37-46. 1992.

(1993), Ryman-Tubb, Nick, “How Thomas Cook used their Neurals”.  Direct Response, September 1993, Vol. 12, No.9.

(1993), Ryman-Tubb, N., “The Use of Neural Networks to Identify the Characteristics of Holiday-Makers”.  Journal of Database marketing, 1(2), p. 140-149.

(1993), Ryman-Tubb, Nick, “A Development Path to Success in Neural Computing”. Expert Systems Applications, Vol. 9, No. 5.

(1993), Ryman-Tubb, N., “Learning to Pump”.  IEE Manufacturing Engineer, Vol. 72, no. 6, Dec. 1993. p. 268-71.

(1994), Ryman-Tubb, Nick, “Neural Computing Inspection”. Quality Today, May 1994.

(1994), Ryman-Tubb, Nick, “Implementation - the Only Sensible Route to Wealth Creating Success: a Range of Applications”. Information Technology Awareness in Engineering, Proceedings, EPSRC, ISBN 0902376506

(1995), Ryman-Tubb, N., “Computers Learn to Smell and Taste”.  Expert Systems, 12 (2), May 1995, p. 157–161.

(1995), Ryman-Tubb, Nick, “A Computer thinks its way into Finance”. Investment Advisor, September 1995.

(1996), Ryman-Tubb, Nick, “THEY ALL STINK!: Chemometrics and the Neural Approach”.  Proc. SPIE Vol. 2878, Sixth, Seventh, and Eighth Workshops on Virtual Intelligence, Academic/Industrial/NASA/Defence Technical Interchange and Tutorials. International Conferences on Neural Networks, Fuzzy Systems, Evolutionary Computing, and Virtual Reality. Mary Lou Padgett and Thomas Lindblad, Eds., p.117, 09/1996.

(1996), Ryman-Tubb, Nick and Dr Bolt, George. “The Thinking Computer -Use of the AMAN Architecture for Integrated Process System Modelling and Optimisation”. Mine & Quarry (Minerals Engineering Society), April 1997, Vol 26, No. 3, p. 36-39.

(1997), Ryman-Tubb, Nick, “Looking at Neural Networks”. Land Mobile, March 1997, p. 34.

(1997), Ryman-Tubb, Nick, “Using Intelligent Software in Telecoms Fraud Detection and Management”. Proceedings of Fighting Mobile Fraud, June 1997, IBC UK.

(1998), Ryman-Tubb, Nick, “Brain Power – Fraud Prevention”. Mobile Asia Pacific, March 1998, p. 20-22.

(1998), Ryman-Tubb, Nick, “Combating Application Fraud”.  Credit Control, 1998, Vol. 19, Issue 11/12, p. 15-20.

(1999), Ryman-Tubb, Nick, “Credit Risk Analysis Software Makes e-Commerce Safer”.  ABA Banking Journal, Vol. 91, 1999.

(1999), Ryman-Tubb, Nick, “Using Advanced Modelling Techniques to Aid Customer Retention and Acquisition”. Journal of Credit Management. July 1999, No. 4, p. 4-7.

(1999), Ryman-Tubb, N., “Prime Time for Sub-Prime”. Journal of Credit Management, November, p. 18-19.

(2000), Ryman-Tubb, Nick, “Impact of e-Commerce on Credit Scoring”.  Credit Control, 2000, Vol. 21, Iss. 3, p. 11-15.

(2000), Ryman-Tubb, Nick, “The Future of Fraud Management – using Advanced Intelligent Techniques”. The Telecommunications Fraud Management Yearbook, 1999-2000, p. 55.

(2000), Ryman-Tubb, Nick,  “An Overview of Credit Scoring Techniques”. Credit Control Journal, Vol. 21, No. 1/2, p. 39-45.

(2000), Ryman-Tubb, Nick, “Credit Scoring and e-Commerce”. Credit Control Journal. Vol. 21, No. 3, p. 11-14.

(2000), Ryman-Tubb, Nick, “The Implications of the Internet on Credit Scoring: A Case Study of Corporate Internet Credit Scoring”.  International Journal of e-Business Strategy Management. Vol. 1, No. 3, February/March 2000, p. 221-226.

(2000), Ryman-Tubb, Nick, “Credit Scoring on-line in real time”, Credit Finance. January 2000.

(2009), Ryman-Tubb, N.: Finding the woods from the trees : Intelligent Fraud Detection Neural-Symbolic Learning Systems in the Detection of Payment Fraud.  In: Engineering Applications of Neural Networks, London. Springer

(2010), Ryman-Tubb, N., d’Avila Garcez, A.S.: SOAR - Sparse Oracle-based Adaptive Rule extraction : knowledge extraction from large-scale datasets to detect credit card fraud.  In: World Congress on Computational Intelligence, Barcelona, Spain, pp. 1-9. IEEE Press

(2011), Ryman-Tubb, N., Krause, P.: Neural Network Rule Extraction to Detect Credit Card Fraud.  In: 12th International Conference on Engineering Applications of Neural Networks (EANN), Corfu, Greece