Artificial Intelligence and Machine Learning (AI & ML) and Sentiment Analysis are said to “predict the future through analysing the past” – the Holy Grail of the finance sector. They can replicate cognitive decisions made by humans yet avoid the behavioural biases inherent in humans.
Processing news data and social media data and classifying (market) sentiment and how it impacts Financial Markets is a growing area of research. The field has recently progressed further with many new “alternative” data sources, such as email receipts, credit/debit card transactions, weather, geo-location, satellite data, Twitter, Micro-blogs and search engine results. AI & ML are gaining adoption in the financial services industry especially in the context of compliance, investment decisions and risk management.
This is a sophisticated conference that not only interrogates and explores the implications of AI & ML in the financial services industry but also goes on to identify the investment opportunities of sharing knowledge and exploiting IP in the finance domain.
Attend this event and earn GARP/CPD credit hours.
UNICOM has registered this program with GARP for Continuing Professional Development (CPD) credits. Attending this program qualifies for 7 credit hours. If you are a Certified ERP® or FRM®, please record this activity in your Credit Tracker.
UNICOM’s Code of Conduct & Views on Diversity
Our approach is that our events are dedicated to providing a harassment-free experience for everyone, regardless of gender, gender identity and expression, age, sexual orientation, disability, physical appearance, body size, race, ethnicity or religion. We do not tolerate intimidation, stalking, harassing photography or recording, sustained disruption of sessions or events, and unwelcome physical contact or sexual attention. We do not tolerate harassment of conference participants in any form. Sexual language and imagery is not appropriate for any conference venue, including talks, workshops, Twitter and other online media. Event participants violating these rules may be sanctioned or expelled from the event without a refund at the discretion of the conference organisers. Please bring your concerns to the immediate attention of the event staff.
Diversity: In our endeavour to be the provider of knowledge to the business community, we understand that this depends on hearing from and listening to a variety of perspectives that come from people of all races, ethnicities, genders, ages, abilities, religions, sexual orientation, and military service. We welcome diverse speakers for all our events, we do not always fully achieve this goal, but it is an ongoing process.
There are three main themes for the day:
Theme 1: Start-ups and New Opportunities in Fintech
Digitization of services is becoming the norm and customers expect more flexibility and interactivity. Reduction in entry costs due to tech support has created space for qualified finance professionals to join or create new start-ups, which has expanded exponentially in India over the last decade.
Theme 2: AI, Alternative data and Quantitative Fund Management using Sentiment Analysis (Presented in two Sessions)
The rise of AI and Machine learning has disrupted, as well as enhanced many aspects of investment models and technologies. Equally applications of Alternative Data in Fintech are growing at a great pace; the question is how to discover new sources of alpha and create strategies and signals. It is also related to alternative data as the use of multiple data sources exploit their hidden coupling. Text analysis, Natural Language Processing and analysis of News as well as investor sentiment is well established. Bringing all these advances together new applications in trading, fund management and risk control continue to emerge. Under this generic theme many aspects will be presented and discussed by presenters and panelists in two sessions.
Theme 3: Security in Fintech
Increasing foothold of fintech poses great challenges in managing the digital identities of individuals and enterprises. Adopting a combination of latest technology and conventional security architectures to prevent cross-platform malware contamination and exploitation of sensitive data in dark market.
AJIT BALAKRISHNAN, CEO, REDIFF.COM, INDIA
What can R and Big Data do to throw new light on classic marketing challenges such as online consumer market segmentation and product recommendations… I will present a few cases of such applications using large scale Indian data and also cast an eye on where Deep Learning could go next.
INDRANEEL FUKE, FOUNDER, CEO, SIMPLEWORKS BUSINESS SOLUTIONS PTE LTD
Going beyond the hype of AI/ML, this session will cover practical use-cases of how AI/ML and Sentiment Analysis can contribute to the digital transformation journey of the BFSI sector. It covers 1) uses cases of facial recognition, OCR scanning, Liveness Detection, fake ID detection, etc from Vision AI perspective, 2) use cases of leveraging of Sentiment Analysis of customer interactions through multiple channels towards cross-sell and up-sell opportunities 3) Leveraging ML for predictions such as next action recommender, next best product to buy, identifying insurance customers at policy renewal risk, etc.
SOUGATA BASU, FOUNDER, CASHRICH
Most retail investors need handholding when navigating numerous investment options and dealing with market uncertainties. Human advisors have been helping investors since a long time. In this discussion, we shall explore whether artificial intelligence and machine learning can provide similar or better level of service when compared to human advisors.
DR. ARUN VERMA, BLOOMBERG L.P, PH.D, SENIOR QUANTITATIVE RESEARCHER & QUANT SOLUTIONS TEAM LEAD
To gain an edge in the markets quantitative hedge fund managers require automated processing to quickly extract actionable information from unstructured and increasingly non-traditional sources of data. The nature of these “alternative data” sources presents challenges that are comfortably addressed through machine learning techniques. We illustrate use of AI and ML techniques that help extract derived signals that have significant alpha or risk premium and lead to profitable trading strategies.
This session will cover the following topics:
♦ The broad application of machine learning in finance
♦ Extracting sentiment from textual data such as news stories and social media content using machine learning algorithms
♦ Construction of scoring models and factors from complex data sets such as supply chain graph, options (implied volatility skew, term structure), Geolocational datasets and ESG (Environmental, Social and Governance)
♦ Robust portfolio construction using multi-factor models by blending in factors derived from alternative data with the traditional factors such as fama-french five-factor model.
GAUTAM MITRA, CEO, OPTIRISK SYSTEMS/VISITING PROFESSOR, UCL
We compute daily trade schedules using a time series of historical equity price data and applying the powerful mathematical concept of Stochastic Dominance. In contrast to classical mean-variance method this approach improves the tail risk as well as the upside of the return. In our recent research we have introduced and combined market sentiment indicators and technical indicators to construct enhanced RSI and momentum filters. These filters restrict the choice of asset universe for trading. Consistent performance improvement achieved in back-testing vindicates our approach.
ASHOK BANERJEE, DEPARTMENTAL HEAD OF FINANCE AND CONTROL, INDIAN INSTITUTE OF MANAGEMENT, CALCUTTA (IIMC), INDIA
ABHILASH MISRA – CEO, NSE ACADEMY
‘The NSE Knowledge Hub’, is a unique Artificial Intelligence (AI) powered learning eco-system to assist the BFSI sector in enhancing skills for their employees and helping academic institutions in preparing future ready talent skilled for the financial services industry.
NSE Knowledge Hub aims to bring world class content closer to learners in a personalized and community learning environment. It allows aggregation, curation, creation and targeting of content which is both learner centric and learner driven. The learning platform is powered by content aggregated from many internal, external, and premium sources, and enhanced by collaborative knowledge sharing from users. With Artificial Intelligence (AI) and Machine Learning (MI) capabilities, the platform provides a comprehensive user-wise report with recommendation on learning opportunities towards skill gap or as a part of progression matrix.
Further, a Learning Experience Platform (LXP), an in-built application on NSE Knowledge Hub platform, functions as a curation and content aggregation layer between an organization’s internal digital learning assets, the vast amount of external content available on the Internet, and user generated content. Enterprises can upskill workforce and enhance employee performance through collaborative innovation. Learners can learn current skills and be future-ready through content/certifications that complements their academic curriculum.
NSE Knowledge Hub delivers a unique learning experience for users and enhanced levels of performance for organizations that produces dramatic business and economic impact and value.
AVEZ SAYED – CRO, SBI GEN INSURANCE
SUNDARA RAMALINGAM N, HEAD – DEEP LEARNING PRACTICE, NVIDIA GRAPHICS PVT LTD, INDIA
The talk will cover the latest technology developments in the field of Artificial Intelligence, with focus on Deep Learning for FSI. It will touch upon how Global FSI companies are adopting AI and Deep Learning for their existing workflows like Risk analytics, Targeted customer campaigns, Document processing, Customer Churn prediction etc.
All aspects of the AI computing ecosystem including Frameworks, advancements in Training & Deployment etc., will be covered during the talk.
SONAL KAPOOR, HEAD, CONSUMER LENDING BUSINESS, FLIPKART
Alternative data has come into the spotlight in financial services, and it presages a significant shift in credit availability for unbanked and underbanked consumers. There are about 70 million credit-invisible consumers in India who lack sufficient traditional credit data. Alternative data is the future of financial inclusion, enabling lenders to extend credit to consumers who have been credit-invisible using next-generation data sources to power both traditional and alternative credit models.
What is alternative data? It includes payment history for electricity, gas and telecom bills, rent payments, repayments to payday lenders, and information such as employment history and educational background. Although alternative data has proved to be valuable and insightful for making lending decisions, until recently, it has not been possible for it to play a meaningful role in credit scoring.
CHANDRASEKHAR SUBRAMANYAM, SR PROFESSOR AND DIRECTOR BUSINESS ANALYTICS CENTER, IFIM BUSINESS SCHOOL
With the popularity of Digital Media large volume of Information about the Company,Industry are available from various sources some paid and unpaid like Bloomberg,Revenpack,News Agencies , Analyst reports , Company Web sites , Blogs , etc. All this is not used for decision making. Majority of these data is in the form of Text , Viedeo , Images etc.. They are also collectively known as unstructured data as they do not comply with standard definition of Data base. Sentiment Analysis is a type of Unstructured data analysis. It is a combination of Natural Language Processing , Statistics & Machine Learning to identify and extract subjective information from text.
This information can be effectively utilised to improve the decision making by extracting sentiment from large volume of such data and combined with other Machine Learning techniques such as Decision Trees, Support Vector Machines and many more techniques. Two use cases will demonstrate how this can be implemented to predict the Rating Transition of Financial instruments and predicting the Enterprise value of companies using real life data. Also talks about some of the challenges involved in data Integration
DAN JOLDZIC, ALEXANDRIA TECHNOLOGY
♦ Technology borrowed from the domain of DNA identification
♦ Design to identify cause and effect in large datasets
♦ Analysis of immense quantity of genomic information
♦ This AI&ML base technology applied to financial analytics
ANTHONY LUCIANI, QUANTITATIVE RESEARCHER, MARKETPYSCH
In this talk Anthony Luciani describes how media analytics are providing new insights into the origins and topping process of asset price bubbles. Examples from price bubbles including the China Composite, cryptocurrencies, housing, and many others will be explored. Recent mathematical models of bubble price action will be augmented with sentiment analysis. Attendees will leave with new models for identifying and taking advantage of speculative manias and panics
ISHAN SHAH, HEAD FOR CONTENT DEVELOPMENT, QUANTINSTI
This workshop will demonstrate the cutting-edge natural language processing research in financial markets. This unique workshop will help you devise new trading strategies using Twitter, news sentiment data. Roadblocks and how to overcome them while working with unstructured data. And how long is the impact of the sentiments on the assets prices. You will learn to predict the market trend by quantifying market sentiments
IVAILO DIMOV, QUANT RESEARCH SOLUTIONS, CTO OFFICE, BLOOMBERG L.P.
Stories on the Bloomberg newsfeed are tagged with “topic codes” containing information about their origin, subject matter, or other characteristics. One might expect that sentiment analysis of news stories may be enhanced by taking into account these topic codes, but the sheer number of topic codes is an obstacle to doing so systematically.
In this talk, we present evidence that some groups of topic codes are indeed associated with stronger sentiment impact on stock prices than others, and discuss a method to condense the mass of topic codes by identifying and retrieving latent factors which may be interpreted as broad themes shared by groups of topic codes.
JACOB GELFAND, CFA, DIRECTOR OF QUANTITATIVE STRATEGY AND RESEARCH, INVESTMENT RISK MANAGEMENT AND KAMILLA KASYMOVA, ASSOCIATE, QUANTITATIVE RESEARCH AND ANALYTICS, NORTHWESTERN MUTUAL
We present a framework for ex-ante analysis of the USD denominated EM Sovereign spreads and respective currencies based on the flow of news in global and local media. The public domain GDELT data is currently being used, but the framework is agnostic to data source, and can be adopted to any data source. We will discuss use cases pertaining to selected countries and spearhead the discussion about predictive qualities of the produced analytics.
ANTOINE FRECHES, SENIOR VP, FICC TRADING, HAITONG INTERNATIONAL SECURITIES
♦ What are the challenges linked to using machine learning techniques to design a systematic investment strategy linked to commodity futures?
♦ What data is relevant and of practical use to attempt to forecast the behaviour of a forward curve?
♦ Can sequence models (RNNs, LSTMs) apply to the noisy data of commodity markets?
♦ How complex can the overall model be for optimal performance and interpretability?
DAN JOLDZIC, ALEXANDRIA TECHNOLOGY
Local source, native publishers may offer an information advantage compared to publications in English. Translation services have typically been sub-optimal for character-based languages, but machine learning allows for classification in the native form, which can lead to significant alpha in forward periods.
RICHARD PETERSON, MANAGING DIRECTOR, MARKETPSYCH
In this talk Dr. Richard Peterson describes how media analytics are providing new insights into the origins and topping process of asset price bubbles. Examples from price bubbles including the China Composite, cryptocurrencies, housing, and many others will be explored. Recent mathematical models of bubble price action will be augmented with sentiment analysis. Attendees will leave with new models for identifying and taking advantage of speculative manias and panics.
PETER SCHWENDNER, PROFESSOR, ZHAW SCHOOL OF MANAGEMENT AND LAW
European sovereign bonds are especially sensitive to the political news flow. Consistent to the current sentiment, market makers adjust factor models in their quotation systems to be prepared for short-term market reactions in the most liquid instruments. We present a correlation influence network case study to make the signs of these factor betas transparent using intraday data analysis. This shows the sentiment of the most active market participants.
MOHAMMAD YOUSUF HUSSAIN, SENIOR TECH AND INNOVATION SPECIALIST, JASMINE22
♦ Overview of techniques explored for intelligent forecasting
♦ Lessons learnt – mistakes that can be avoided when using ML for forecasting
♦ Extracting signals from alternative data and integrating them into trading strategies