Model selection is performed. First information is obtained from a user about a presenting issue. The first information is used within a supermodel to identify an underlying issue and an associated sub model for providing a solution to the underlying issue. A Bayesian network structure is used to identify the underlying issue and the associated sub model. The sub model obtains additional information about the underlying issue from the user. The sub model uses the additional information to identify a solution to the underlying issue.

Model selection for decision support systems

Partial table of contents: Trading----The Last Frontier. The Odds Against You. INDIVIDUAL PSYCHOLOGY. Fantasy Versus Reality. Self--Destructiveness. Trading Lessons from AA. Winners and Losers. MASS PSYCHOLOGY. What Is the Market?. The Market Crowd and You. Managing Versus Forecasting. CLASSICAL CHART ANALYSIS. Support and Resistance. Trendlines. Chart Patterns. COMPUTERIZED TECHNICAL ANALYSIS. Moving Averages. The Directional System. Williams %R. Relative Strength Index. THE NEGLECTED ESSENTIALS. Volume--Based Indicators. Herrick Payoff Index. STOCK MARKET INDICATORS. New High--New Low Index. PSYCHOLOGICAL INDICATORS. Consensus Indicators. NEW INDICATORS. Elder--Ray. TRADING SYSTEMS. Triple Screen Trading System. Channel Trading Systems. RISK MANAGEMENT. Money Management. Afterword. Sources. Index.

Study Guide for Trading for a Living: Psychology, Trading Tactics, Money Management

We present an efficient and non-interactive method for Text Classification while preserving the privacy of the content using Fully Homomorphic Encryption (FHE). Our solution (named Priv ate F ast T ext (PrivFT)) provides two services: 1) making inference of encrypted user inputs using a plaintext model and 2) training an effective model using an encrypted dataset. For inference, we use a pre-trained plaintext model and outline a system for homomorphic inference on encrypted user inputs with zero loss to prediction accuracy compared to the non-encrypted version. In the second part, we show how to train a supervised model using fully encrypted data to generate an encrypted model. For improved performance, we provide a GPU implementation of the Cheon-Kim-Kim-Song (CKKS) FHE scheme that shows 1 to 2 orders of magnitude speedup against existing implementations. We build PrivFT on top of our FHE engine in GPUs to achieve a run time per inference of 0.17 seconds for various Natural Language Processing (NLP) public datasets. Training on a relatively large encrypted dataset is more computationally intensive requiring 5.04 days.

PrivFT: Private and Fast Text Classification With Homomorphic Encryption

The recent booming of AI in FinTech evidences the significant developments and potential of AI for making smart FinTech, economy, finance and society. AI-empowered smart FinTech has emerged as a sexy and increasingly critical area in AI, data science, economics, finance, and other relevant research disciplines and business domains. This trend was built on the long history of AI in finance, and the new-generation AI, data science and machine learning are fundamentally and seamlessly transforming the vision, missions, objectives, paradigms, theories, approaches, tools and social aspects of economics and finance and driving smart FinTech. AI is empowering more personalized and advanced and better, safer and newer mainstream and alternative economic-financial mechanisms, products, models, services, systems, and applications. This review summarizes the lasting research on AI in finance and focuses on creating a comprehensive, multidimensional and economic-financial problem-driven research landscape of the roles, research directions and opportunities of AI in new-generation FinTech and finance.

AI in Finance: A Review

Increasing use of machine learning (ML) technologies in privacy-sensitive domains such as medical diagnoses, lifestyle predictions, and business decisions highlights the need to better understand if these ML technologies are introducing leakage of sensitive and proprietary training data. In this paper, we focus on model inversion attacks where the adversary knows non-sensitive attributes about records in the training data and aims to infer the value of a sensitive attribute unknown to the adversary, using only black-box access to the target classiﬁcation model. We ﬁrst devise a novel conﬁdence score-based model inversion attribute inference attack that signiﬁcantly outperforms the state-of-the-art. We then introduce a label-only model inversion attack that relies only on the model’s predicted labels but still matches our conﬁdence score-based attack in terms of attack effectiveness. We also extend our attacks to the scenario where some of the other (non-sensitive) attributes of a target record are unknown to the adversary. We evaluate our attacks on two types of machine learning models, decision tree and deep neural network, trained on three real datasets. Moreover, we empirically demonstrate the disparate vulnerability of model inversion attacks, i.e., speciﬁc groups in the training dataset (grouped by gender, race, etc.) could be more vulnerable to model inversion attacks.

Are Your Sensitive Attributes Private? Novel Model Inversion Attribute Inference Attacks on Classification Models

This paper is based on research applying artificial intelligence to problems of trading financial markets The paper presents a background to various financial market trading problems of interest A model system and strategy for developing decision support systems to trade financial markets and forecast asset price movements is then presented and discussed The problems of interest are those where the variables are not constant in time The time series of data representing the dynamics of price movements in financial markets are nonlinear and nonstationary The forecasting techniques developed are applied to examples of foreign exchange trading involving the directional movement only of the four major currencies of British pound sterling, Deutschemark, Swiss franc and Japanese yen against the US dollar Examples demonstrate the forecasting output and performance of the models as measured by profit and loss returns

M.A. Pearson

Papers

Artificial intelligence in financial markets