Technavio is a leading global technology research and advisory company. Their research and analysis focus on emerging market trends and provides actionable insights to help businesses identify market opportunities and develop effective strategies to optimize their market positions. With over 500 specialized analysts, Technavio's report library consists of more than 17,000 reports and counting, covering 800 technologies, spanning across 50 countries. Their client base consists of enterprises of all sizes, including more than 100 Fortune 500 companies. This growing client base relies on Technavio's comprehensive coverage, extensive research, and actionable market insights to identify opportunities in existing and potential markets and assess their competitive positions within changing market scenarios.

School of the Built Environment, Oxford Brookes University, Oxford, OX3 0BP, UK. Abstract: This paper provides the state of the art of data science in economics. Through a novel taxonomy of applications and methods advances in data science are investigated. The data science advances are investigated in three individual classes of deep learning models, ensemble models, and hybrid models. Application domains include stock market, marketing, E-commerce, corporate banking, and cryptocurrency. Prisma method, a systematic literature review methodology is used to ensure the quality of the survey. The findings revealed that the trends are on advancement of hybrid models as more than 51% of the reviewed articles applied hybrid model. On the other hand, it is found that based on the RMSE accuracy metric, hybrid models had higher prediction accuracy than other algorithms. While it is expected the trends go toward the advancements of deep learning models. LSDL Large-Scale Deep Learning LSTM Long Short-Term Memory LWDNN List-Wise Deep Neural Network MACN Multi-Agent Collaborated Network MB-LSTM Multivariate Bidirectional LSTM MDNN Multilayer Deep Neural Network MFNN Multi-Filters Neural Network MLP Multiple Layer Perceptron MLP Multi-Layer Perceptron NNRE Neural Network Regression Ensemble O-LSRM Optimal Long Short-Term Memory PCA Principal Component Analysis pSVM Proportion Support Vector Machines RBFNN Radial Basis Function Neural Network RBM Restricted Boltzmann Machine REP Reduced Error Pruning RF Random Forest RFR Random Forest Regression RNN Recurrent Neural Network SAE Stacked Autoencoders SLR Stepwise Linear Regressions SN-CFM Similarity, Neighborhood-Based Collaborative Filtering Model STI Stock Technical Indicators SVM Support Vector Machine SVR Support Vector Regression SVRE Support Vector Regression Ensemble, TDFA Time-Driven Feature-Aware TS-GRU Two-Stream GRU WA Wavelet Analysis WT Wavelet Transforms 1. Introduction Application of data science in different disciplines is exponentially increasing. Because data science has had tremendous progresses in analysis and use of data. Like other disciplines, economics has benefited from the advancements of data science. Advancements of data science in economics have been progressive and have recorded promising results in the literature.

Organisations continually strive to strike a balance between increasing equipment efficiency and reducing overall maintenance costs. Asset service engineers and quality departments across industries, such as airlines, oil & gas, pharmaceuticals, telecom, automobiles, and others, are pushed continuously to optimise their planning and operational expenses. As the Industry 4.0 paradigm continues to evolve, the Digital Twins technology provides a pragmatic opportunity to leverage virtual models to also enable impact points such as to predict failures, prescribe actions, and support digital supply chain networks. A digital twin, by definition, offers a seamless convergence of the physical and digital worlds -- creating an ever-evolving digital profile of a physical asset based on its historical and current behaviour. The idea of using digital models to optimise asset efficiency is not new.

Recently, CNN object detectors have achieved high accuracy on remote sensing images but require huge labor and time costs on annotation. In this paper, we propose a new uncertainty-based active learning which can select images with more information for annotation and detector can still reach high performance with a fraction of the training images. Our method not only analyzes objects' classification uncertainty to find least confident objects but also considers their regression uncertainty to declare outliers. Besides, we bring out two extra weights to overcome two difficulties in remote sensing datasets, class-imbalance and difference in images' objects amount. We experiment our active learning algorithm on DOTA dataset with CenterNet as object detector. We achieve same-level performance as full supervision with only half images. We even override full supervision with 55% images and augmented weights on least confident images.

Deploying big-data Machine Learning (ML) services in a cloud environment presents a challenge to the cloud vendor with respect to the cloud container configuration sizing for any given customer use case. OracleLabs has developed an automated framework that uses nested-loop Monte Carlo simulation to autonomously scale any size customer ML use cases across the range of cloud CPU-GPU "Shapes" (configurations of CPUs and/or GPUs in Cloud containers available to end customers). Moreover, the OracleLabs and NVIDIA authors have collaborated on a ML benchmark study which analyzes the compute cost and GPU acceleration of any ML prognostic algorithm and assesses the reduction of compute cost in a cloud container comprising conventional CPUs and NVIDIA GPUs.

If you have learned temporal parallelism used to speed up CPU execution, you came across instruction pipelines aka pipeline processing. In pipeline processing, you will have many instructions in different stages of execution. The term "Data Pipeline" is a misnomer representing a high bandwidth communication channel used for data transportation between a source system and a destination. In certain cases the destination is called a sink. Pipelines by definition allow flow of a fluid automatically from one end to the other end, when one end is connected to a source.

In real life, providing security for a set of large areas by covering the area with Unmanned Aerial Vehicles (UAVs) is a difficult problem that consist of multiple objectives. These difficulties are even greater if the area coverage must continue throughout a specific time window. We address this by considering a Vehicle Routing Problem with Time Windows (VRPTW) variation in which capacity of agents is one and each customer (target area) must be supplied with more than one vehicles simultaneously without violating time windows. In this problem, our aim is to find a way to cover all areas with the necessary number of UAVs during the time windows, minimize the total distance traveled, and provide a fast solution by satisfying the additional constraint that each agent has limited fuel. We present a novel algorithm that relies on clustering the target areas according to their time windows, and then incrementally generating transportation problems with each cluster and the ready UAVs. Then we solve transportation problems with the simplex algorithm to generate the solution. The performance of the proposed algorithm and other implemented algorithms to compare the solution quality is evaluated on example scenarios with practical problem sizes.

This paper presents unifying results for subspace identification (SID) and dynamic mode decomposition (DMD) for autonomous dynamical systems. We observe that SID seeks to solve an optimization problem to estimate an extended observability matrix and a state sequence that minimizes the prediction error for the state-space model. Moreover, we observe that DMD seeks to solve a rank-constrained matrix regression problem that minimizes the prediction error of an extended autoregressive model. We prove that existence conditions for perfect (error-free) state-space and low-rank extended autoregressive models are equivalent and that the SID and DMD optimization problems are equivalent. We exploit these results to propose a SID-DMD algorithm that delivers a provably optimal model and that is easy to implement. We demonstrate our developments using a case study that aims to build dynamical models directly from video data.

Coherent Gradients is a recently proposed hypothesis to explain why over-parameterized neural networks trained with gradient descent generalize well even though they have sufficient capacity to memorize the training set. Inspired by random forests, Coherent Gradients proposes that (Stochastic) Gradient Descent (SGD) finds common patterns amongst examples (if such common patterns exist) since descent directions that are common to many examples add up in the overall gradient, and thus the biggest changes to the network parameters are those that simultaneously help many examples. The original Coherent Gradients paper validated the theory through causal intervention experiments on shallow, fully connected networks on MNIST. In this work, we perform similar intervention experiments on more complex architectures (such as VGG, Inception and ResNet) on more complex datasets (such as CIFAR-10 and ImageNet). Our results are in good agreement with the small scale study in the original paper, thus providing the first validation of coherent gradients in more practically relevant settings. We also confirm in these settings that suppressing incoherent updates by natural modifications to SGD can significantly reduce overfitting--lending credence to the hypothesis that memorization occurs when few examples are responsible for most of the gradient used in the update. Furthermore, we use the coherent gradients theory to explore a new characterization of why some examples are learned earlier than other examples, i.e., "easy" and "hard" examples.

This paper investigates the use of a networked system ($e.g.$, swarm of robots, smart grid, sensor network) to monitor a time-varying phenomenon of interest in the presence of communication and computation latency. Recent advances in edge computing have enabled processing to be spread across the network, hence we investigate the fundamental computation-communication trade-off, arising when a sensor has to decide whether to transmit raw data (incurring communication delay) or preprocess them (incurring computational delay) in order to compute an accurate estimate of the state of the phenomenon of interest. We propose two key contributions. First, we formalize the notion of $processing$ $network$. Contrarily to $sensor$ $and$ $communication$ $networks$, where the designer is concerned with the design of a suitable communication policy, in a processing network one can also control when and where the computation occurs in the network. The second contribution is to provide analytical results on the optimal preprocessing delay ($i.e.$, the optimal time spent on computations at each sensor) for the case with a single sensor and multiple homogeneous sensors. Numerical results substantiate our claims that accounting for computation latencies (both at sensor and estimator side) and communication delays can largely impact the estimation accuracy.