High-Frequency Trading with Machine Learning Algorithms and Limit Order Book Data

This survey starts with a general overview of the strategies for stock price change predictions based on market data and in particular Limit Order Book (LOB) data. The main discussion is devoted to the systematic analysis, comparison, and critical evaluation of the state-of-the-art studies in the research area of stock price movement predictions based on LOB data. LOB and Order Flow data are two of the most valuable information sources available to traders on the stock markets. Academic researchers are actively exploring the application of different quantitative methods and algorithms for this type of data to predict stock price movements. With the advancements in machine learning and subsequently in deep learning, the complexity and computational intensity of these models was growing, as well as the claimed predictive power. Some researchers claim accuracy of stock price movement prediction well in excess of 80%. These models are now commonly employed by automated market-making programs to set bids and ask quotes. If these results were also applicable to arbitrage trading strategies, then those algorithms could make a fortune for their developers. Thus, the open question is whether these results could be used to generate buy and sell signals that could be exploited with active trading. Therefore, this survey paper is intended to answer this question by reviewing these results and scrutinising their reliability. The ultimate conclusion from this analysis is that although considerable progress was achieved in this direction, even the state-of-art models can not guarantee a consistent profit in active trading. Taking this into account several suggestions for future research in this area were formulated along the three dimensions: input data, model’s architecture, and experimental setup. In particular, from the input data perspective, it is critical that the dataset is properly processed, up-to-date, and its size is sufficient for the particular model training. From the model architecture perspective, even though deep learning models are demonstrating a stronger performance than classical models, they are also more prone to over-fitting. To avoid over-fitting it is suggested to optimize the feature space, as well as a number of layers and neurons, and apply dropout functionality. The over-fitting problem can be also addressed by optimising the experimental setup in several ways: Introducing the early stopping mechanism; Saving the best weights of the model achieved during the training; Testing the model on the out-of-sample data, which should be separated from the validation and training samples. Finally, it is suggested to always conduct the trading simulation under realistic market conditions considering transactions costs, bid–ask spreads, and market impact.

An experimental approach to the study of limit order books lies in the availability of data. Most of the results presented in this book - in any case, those we have produced ourselves - use the Thomson Reuters Tick History (TRTH) database. All exchange-traded assets worldwide are present in the TRTH database, where they are identified by their Reuters Identification Code (RIC). Similar to most historical databases directly provided by the exchanges, the TRTH data come into the form of two separate files, a trade file recording all transactions, and an event file recording every change in the limit order book. Some very specific information, such as traders’ identities, cannot be publicly disclosed for obvious confidentiality reasons, but in theory, one could reconstruct the sequence of order arrivals of all types using this trade and event files. After explaining the algorithm used for the processing of limit order book data, we describe the specific data sets that have been used at various places in this book. That way, our results can be reproduced, extended and, of course, challenged, based on the very same data sets we have used. Limit Order Book Data Processing Because one cannot distinguish market orders from cancellations just by observing changes in the limit order book (the “event” file), and since, the timestamps of the “trade” and “event” files are asynchronous , we use a matching procedure to reconstruct the order book events. In a nutshell, we proceed as follows for each stock and each trading day: 1. Parse the “event” file to compute order book state variations: • If the variation is positive (volume at one or more price levels has increased), then label the event as a limit order. • If the variation is negative (volume at one or more price levels has decreased), then label the event as a “likely market order”. • If no variation—this happens when there is just a renumbering in the field “Level” that does not affect the state of the book—do not count an event. 2. Parse the “trade” file and for each trade: • Compare the trade price and volume to likely market orders whose timestamps are in, where t Tr is the trade timestamp and Δ t is a predefined, market-dependent time window.

Undernutrition among children under the age of five is a major public health concern, especially in developing countries. This study aimed to use machine learning (ML) algorithms to predict undernutrition and identify its associated factors. Secondary data analysis of the 2017 Multiple Indicator Cluster Survey (MICS) was performed using R and Python. The main outcomes of interest were undernutrition (stunting: height-for-age (HAZ) < -2 SD; wasting: weight-for-height (WHZ) < -2 SD; and underweight: weight-for-age (WAZ) < -2 SD). Seven ML algorithms were trained and tested: linear discriminant analysis (LDA), logistic model, support vector machine (SVM), random forest (RF), least absolute shrinkage and selection operator (LASSO), ridge regression, and extreme gradient boosting (XGBoost). The ML models were evaluated using the accuracy, confusion matrix, and area under the curve (AUC) receiver operating characteristics (ROC). In total, 8564 children were included in the final analysis. The average age of the children was 926 days, and the majority were females. The weighted prevalence rates of stunting, wasting, and underweight were 17%, 7%, and 12%, respectively. The accuracies of all the ML models for wasting were (LDA: 84%; Logistic: 95%; SVM: 92%; RF: 94%; LASSO: 96%; Ridge: 84%, XGBoost: 98%), stunting (LDA: 86%; Logistic: 86%; SVM: 98%; RF: 88%; LASSO: 86%; Ridge: 86%, XGBoost: 98%), and for underweight were (LDA: 90%; Logistic: 92%; SVM: 98%; RF: 89%; LASSO: 92%; Ridge: 88%, XGBoost: 98%). The AUC values of the wasting models were (LDA: 99%; Logistic: 100%; SVM: 72%; RF: 94%; LASSO: 99%; Ridge: 59%, XGBoost: 100%), for stunting were (LDA: 89%; Logistic: 90%; SVM: 100%; RF: 92%; LASSO: 90%; Ridge: 89%, XGBoost: 100%), and for underweight were (LDA: 95%; Logistic: 96%; SVM: 100%; RF: 94%; LASSO: 96%; Ridge: 82%, XGBoost: 82%). Age, weight, length/height, sex, region of residence and ethnicity were important predictors of wasting, stunting and underweight. The XGBoost model was the best model for predicting wasting, stunting, and underweight. The findings showed that different ML algorithms could be useful for predicting undernutrition and identifying important predictors for targeted interventions among children under five years in Ghana.

ObjectiveEnhanced technology in computer and internet has driven scale and quality of data to be improved in various areas including healthcare sectors. Machine Learning (ML) has played a pivotal role in efficiently analyzing those big data, but a general misunderstanding of ML algorithms still exists in applying them (e.g., ML techniques can settle a problem of small sample size, or deep learning is the ML algorithm). This paper reviewed the research of diagnosing mental illness using ML algorithm and suggests how ML techniques can be employed and worked in practice.MethodsResearches about mental illness diagnostic using ML techniques were carefully reviewed. Five traditional ML algorithms-Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN)-frequently used for mental health area researches were systematically organized and summarized.ResultsBased on literature review, it turned out that Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN) were frequently employed in mental health area, but many researchers did not clarify the reason for using their ML algorithm though every ML algorithm has its own advantages. In addition, there were several studies to apply ML algorithms without fully understanding the data characteristics.ConclusionResearchers using ML algorithms should be aware of the properties of their ML algorithms and the limitation of the results they obtained under restricted data conditions. This paper provides useful information of the properties and limitation of each ML algorithm in the practice of mental health.

We introduce new machine learning methods for clustering traders who are actively trading in a modern electronic exchange which uses a matching engine to track aggregate and individual‐level limit order books. Each trader's individual limit order book is centered (with the current best bid and ask prices acting as a central reference), and the patterns in the individual limit order books are identified using a Wasserstein distance. The method is illustrated using simulated limit order book data and limit order book data from a stock exchange in Canada.

Air pollution in Macau has become a serious problem following the Pearl River Delta’s (PRD) rapid industrialization that began in the 1990s. With this in mind, Macau needs an air quality forecast system that accurately predicts pollutant concentration during the occurrence of pollution episodes to warn the public ahead of time. Five different state-of-the-art machine learning (ML) algorithms were applied to create predictive models to forecast PM2.5, PM10, and CO concentrations for the next 24 and 48 h, which included artificial neural networks (ANN), random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), and multiple linear regression (MLR), to determine the best ML algorithms for the respective pollutants and time scale. The diurnal measurements of air quality data in Macau from 2016 to 2021 were obtained for this work. The 2020 and 2021 datasets were used for model testing, while the four-year data before 2020 and 2021 were used to build and train the ML models. Results show that the ANN, RF, XGBoost, SVM, and MLR models were able to provide good performance in building up a 24-h forecast with a higher coefficient of determination (R2) and lower root mean square error (RMSE), mean absolute error (MAE), and biases (BIAS). Meanwhile, all the ML models in the 48-h forecasting performance were satisfactory enough to be accepted as a two-day continuous forecast even if the R2 value was lower than the 24-h forecast. The 48-h forecasting model could be further improved by proper feature selection based on the 24-h dataset, using the Shapley Additive Explanations (SHAP) value test and the adjusted R2 value of the 48-h forecasting model. In conclusion, the above five ML algorithms were able to successfully forecast the 24 and 48 h of pollutant concentration in Macau, with the RF and SVM models performing the best in the prediction of PM2.5 and PM10, and CO in both 24 and 48-h forecasts.

This study presents a comparative analysis of the classification performance of facial and emotion recognition systems using Machine Learning (ML) and Deep Learning (DL) algorithms. The primary objective of this work is to evaluate the applicability of emotion recognition in fields such as psychotherapy and crime analysis, using the FER-2013 dataset.The study was conducted with ML algorithms such as Support Vector Machines (SVM), Random Forest (RF), K-Nearest Neighbor (KNN), Decision Trees, and Gradient Boosting, as well as the DL algorithm, Convolutional Neural Network (CNN). Supported by the application of feature selection, preprocessing, and feature extraction techniques, the model’s performance was measured using standard metrics such as accuracy, precision, F1-score, and AUC-ROC.The experimental results showed that the highest classification accuracy (46.61%) was achieved with the CNN model. While the ML models generally offered lower accuracy, they provided advantages in terms of computational efficiency in specific scenarios.This study aims to contribute to the literature by providing a comparative analysis of ML and DL algorithms and by highlighting the effect of data preprocessing on performance. The findings set targets for future work, such as real-time system integration and hybrid model development.

The rapid growth of the Internet and information technologies and also the diminution of the price of hardware components like wireless sensors leads to the fast growth in Wireless Sensor Network (WSN). The WSN is a bunch/group of sensors that are located across the area, in order to monitor and determine environmental conditions such as temperature, humidity, vibrations, wind, water levels, pollution levels. WSNs are susceptible to major attacks like Denial of Service (DOS), Wormhole attack, Sinkhole attack, etc. The main threat to the WSN is because of the broadcast nature of the nodes in the network. Therefore, the security of WSNs is the essential part that must be done. Hence, to overcome these problems or threats, we are trying to detect it using AI technology. With the expanding fields of Machine Learning and Deep Learning, we can apply various algorithms in order to classify different types of attacks. Once we detect the attack properly, we can prevent it accordingly. We are using WSN-DS. It has 4 classes of attacks which are Grayhole, Blackhole, TDMA(Scheduling), and Flooding which comes under the category of DOS attacks. In this chapter, we have analysed and compared the accuracies of 5 main machine learning classification algorithms. Also, we have analysed the 1 deep learning algorithm. The ANN (Artificial Neural Network) and 5 machine learning algorithms have been trained on the dataset. Furthermore, we have used K-fold cross-validation to get even more accurate predictions. After analysis of these algorithms, we came to the point that, the Machine Learning algorithms like Random Forest, Support Vector Machines and Deep Learning algorithm, namely, Artificial Neural Network can help us for detecting intrusions in the system or network. This will help researchers in designing their own machine learning model on top of our suggested model.

The paper considers a general semi-Markov model for limit order books with two states that incorporates price changes that are not fixed to one tick. Furthermore, we introduce an even more general case of the semi-Markov model for limit order books that incorporates an arbitrary number of states for the price changes. For both cases, the justifications, diffusion limits, implementations and numerical results are presented for different limit order book data: Apple, Amazon, Google, Microsoft, Intel on 21 June 2012 and Cisco, Facebook, Intel, Liberty Global, Liberty Interactive, Microsoft, Vodafone from 3 November 2014 to 7 November 2014.

Slope stability prediction using integrated metaheuristic and machine learning approaches: A comparative study

Background and aimsThe birth weight of a newborn is a crucial factor that affects their overall health and future well-being. Low birth weight (LBW) is a widespread global issue, which the World Health Organization defines as weighing less than 2,500 g. LBW can have severe negative consequences on an individual’s health, including neonatal mortality and various health concerns throughout their life. To address this problem, this study has been conducted using BDHS 2017–2018 data to uncover important aspects of LBW using a variety of machine learning (ML) approaches and to determine the best feature selection technique and best predictive ML model.MethodsTo pick out the key features, the Boruta algorithm and wrapper method were used. Logistic Regression (LR) used as traditional method and several machine learning classifiers were then used, including, DT (Decision Tree), SVM (Support Vector Machine), NB (Naïve Bayes), RF (Random Forest), XGBoost (eXtreme Gradient Boosting), and AdaBoost (Adaptive Boosting), to determine the best model for predicting LBW. The model’s performance was evaluated based on the specificity, sensitivity, accuracy, F1 score and AUC value.ResultsResult shows, Boruta algorithm identifies eleven significant features including respondent’s age, highest education level, educational attainment, wealth index, age at first birth, weight, height, BMI, age at first sexual intercourse, birth order number, and whether the child is a twin. Incorporating Boruta algorithm’s significant features, the performance of traditional LR and ML methods including DT, SVM, NB, RF, XGBoost, and AB were evaluated where LR, had a specificity, sensitivity, accuracy and F1 score of 0.85, 0.5, 85.15% and 0.915. While the ML methods DT, SVM, NB, RF, XGBoost, and AB model’s respective accuracy values were 85.35%, 85.15%, 84.54%, 81.18%, and 84.41%. Based on the specificity, sensitivity, accuracy, F1 score and AUC, RF (specificity = 0.99, sensitivity = 0.58, accuracy = 85.86%, F1 score = 0.9243, AUC = 0.549) outperformed the other methods. Both the classical (LR) and machine learning (ML) models’ performance has improved dramatically when important characteristics are extracted using the wrapper method. The LR method identified five significant features with a specificity, sensitivity, accuracy and F1 score of 0.87, 0.33, 87.12% and 0.9309. The region, whether the infant is a twin, and cesarean delivery were the three key features discovered by the DT and RF models, which were implemented using the wrapper technique. All three models had the identical F1 score of 0.9318. However, “child is twin” was recognized as a significant feature by the SVM, NB, and AB models, with an F1 score of 0.9315. Ultimately, with an F1 score of 0.9315, the XGBoost model recognized “child is twin” and “age at first sex” as relevant features. Random Forest again beat the other approaches in this instance.ConclusionsThe study reveals Wrapper method as the optimal feature selection technique. The ML method outperforms traditional methods, with Random Forest (RF) being the most effective predictive model for Low-Birth-Weight prediction. The study suggests that policymakers in Bangladesh can mitigate low birth weight newborns by considering identified risk factors.

Gesture recognition is a topic in computer science and language technology that aims to interpret human gestures with computer programs and many different algorithms. It can be seen as the way computers can understand human body language. Today, the main interaction tools between computers and humans are still the keyboard and mouse. Gesture recognition can be used as a tool for communication with the machine and interaction without any mechanical device such as a keyboard or mouse. In this paper, we present the results of a comparison of eight different machine learning (ML) classifiers in the task of human hand gesture recognition and classification to explore how to efficiently implement one or more tested ML algorithms on an 8-bit AVR microcontroller for on-line human gesture recognition with the intention to gesturally control the mobile robot. The 8-bit AVR microcontrollers are still widely used in the industry, but due to their lack of computational power and limited memory, it is a challenging task to efficiently implement ML algorithms on them for on-line classification. Gestures were recorded by using inertial sensors, gyroscopes, and accelerometers placed at the wrist and index finger. One thousand and eight hundred (1800) hand gestures were recorded and labelled. Six important features were defined for the identification of nine different hand gestures using eight different machine learning classifiers: Decision Tree (DT), Random Forests (RF), Logistic Regression (LR), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM) with linear kernel, Naïve Bayes classifier (NB), K-Nearest Neighbours (KNN), and Stochastic Gradient Descent (SGD). All tested algorithms were ranged according to Precision, Recall, and F1-score (abb.: P-R-F1). The best algorithms were SVM (P-R-F1: 0.9865, 0.9861, and 0.0863), and RF (P-R-F1: 0.9863, 0.9861, and 0.0862), but their main disadvantage is their unusability for on-line implementations in 8-bit AVR microcontrollers, as proven in the paper. The next best algorithms have had only slightly poorer performance than SVM and RF: KNN (P-R-F1: 0.9835, 0.9833, and 0.9834) and LR (P-R-F1: 0.9810, 0.9810, and 0.9810). Regarding the implementation on 8-bit microcontrollers, KNN has proven to be inadequate, like SVM and RF. However, the analysis for LR has proved that this classifier could be efficiently implemented on targeted microcontrollers. Having in mind its high F1-score (comparable to SVM, RF, and KNN), this leads to the conclusion that the LR is the most suitable classifier among tested for on-line applications in resource-constrained environments, such as embedded devices based on 8-bit AVR microcontrollers, due to its lower computational complexity in comparison with other tested algorithms.

After radical prostatectomy (RP), one-third of patients will experience biochemical recurrence (BCR), which is associated with subsequent metastasis and cancer-specific mortality. We employed machine learning (ML) algorithms to predict BCR after RP, and compare them with traditional regression models and nomograms. Utilizing a prospective Uro-oncology registry, 18 clinicopathological parameters of 1130 consecutive patients who underwent RP (2009-2018) were recorded, yielding over 20,000 data points for analysis. The data set was split into a 70:30 ratio for training and validation. Three ML models: Naïve Bayes (NB), random forest (RF), and support vector machine (SVM) were studied, and compared with traditional regression models and nomograms (Kattan, CAPSURE, John Hopkins [JHH]) to predict BCR at 1, 3, and 5 years. Over a median follow-up of 70.0 months, 176 (15.6%) developed BCR, at a median time of 16.0 months (interquartile range [IQR]: 11.0-26.0). Multivariate analyses demonstrated strongest association of BCR with prostate-specific antigen (PSA) (p: 0.015), positive surgical margins (p < 0.001), extraprostatic extension (p: 0.002), seminal vesicle invasion (p: 0.004), and grade group (p < 0.001). The 3 ML models demonstrated good prediction of BCR at 1, 3, and 5 years, with the area under curves (AUC) of NB at 0.894, 0.876, and 0.894, RF at 0.846, 0.875, and 0.888, and SVM at 0.835, 0.850, and 0.855, respectively. All models demonstrated (1) robust accuracy (>0.82), (2) good calibration with minimal overfitting, (3) longitudinal consistency across the three time points, and (4) inter-model validity. The ML models were comparable to traditional regression analyses (AUC: 0.797, 0.848, and 0.862) and outperformed the three nomograms: Kattan (AUC: 0.815, 0.798, and 0.799), JHH (AUC: 0.820, 0.757, and 0.750) and CAPSURE nomograms (AUC: 0.706, 0.720, and 0.749) (p < 0.001). Supervised ML algorithms can deliver accurate performances and outperform nomograms in predicting BCR after RP. This may facilitate tailored care provisions by identifying high-risk patients who will benefit from multimodal therapy.

Objectives: Language detection is the process of identifying a language associated with a text. The proposed system aims to detect the Dravidian language that is associated with the given text using different machine learning and deep learning algorithms. The paper presents an empirical analysis of the results obtained using the different models. It also aims to evaluate the performance of a language agnostic model for the purpose of language detection. Method: An empirical analysis of Dravidian language identification in social media text using machine learning and deep learning approaches with k-fold cross validation has been implemented. The identification of Dravidian languages, including Tamil, Malayalam, Tamil Code Mix, and Malayalam Code Mix, is performed using both machine learning (ML) and deep learning algorithms. The machine learning algorithms used for language detection are Naive Bayes (NB), Multinomial Logistic Regression (MLR), Support Vector Machine (SVM), and Random Forest (RF). The supervised Deep Learning (DL) models used include BERT, mBERT and language agnostic models. Findings: The language agnostic model outperform all other models considering the task of language detection in Dravidian languages. The results of both the ML and DL models are analyzed empirically with performance measures like accuracy, precision, recall, and f1-score. The accuracy associated with different machine learning algorithms varies from 85% to 89%. It is evident from the experimental result that the deep learning model outperformed with an accuracy of 98%. Novelty: The proposed system emphasizes on the use of the language agnostic model to implement the process of detecting Dravidian languages associated with the given text which provides a promising result of 98% accuracy which is higher than the existing methodologies. Keywords: Language, Machine learning, Deep learning, Transformer model, Encoder, Decoder

In the era of artificial intelligence, machine learning methods are successfully used in various fields. Machine learning has attracted extensive attention from investors in the financial market, especially in stock price prediction. However, one argument for the machine learning methods used in stock price prediction is that they are black-box models which are difficult to interpret. In this paper, we focus on the future stock price prediction with the historical stock price by machine learning and deep learning methods, such as support vector machine (SVM), random forest (RF), Bayesian classifier (BC), decision tree (DT), multilayer perceptron (MLP), convolutional neural network (CNN), bi-directional long-short term memory (BiLSTM), the embedded CNN, and the embedded BiLSTM. Firstly, we manually design several financial time series where the future price correlates with the historical stock prices in pre-designed modes, namely the curve-shape-feature (CSF) and the non-curve-shape-feature (NCSF) modes. In the CSF mode, the future prices can be extracted from the curve shapes of the historical stock prices. Conversely, in the NCSF mode, they can’t. Secondly, we apply various algorithms to those pre-designed and real financial time series. We find that the existing machine learning and deep learning algorithms fail in stock price prediction because in the real financial time series, less information of future prices is contained in the CSF mode, and perhaps more information is contained in the NCSF. Various machine learning and deep learning algorithms are good at handling the CSF in historical data, which are successfully applied in image recognition and natural language processing. However, they are inappropriate for stock price prediction on account of the NCSF. Therefore, accurate stock price prediction is the key to successful investment, and new machine learning algorithms handling the NCSF series are needed.&#x0D;