Goto

Collaborating Authors

Results


An Intuitive Study of Time Series Analysis

#artificialintelligence

A time series data is a set of observation on the value that a variable takes of different time, such data may be collected at regular time intervals such as daily stock price, monthly money supply figures, annual GDP etc. Time series data have a natural temporal ordering. This makes time series analysis distinct from other common data analysis problems in which there is no natural order of the observation. In simple word we can say, the data which are collected in according to time is called time series data. On the other hand, the data which are collected by observing many subject at the same point of time is called cross sectional data. A time series is a set of observations meas ured at time or space intervals arranged in chrono logical order.


What is time-series data, and why are we building a time-series database (TSDB)?

#artificialintelligence

Like all good superheroes, every company has its own origin story explaining why they were created and how they grew over time. This article covers the origin story of QuestDB and frames it with an introduction to time series databases to show where we sit in that landscape today. Time series is a succession of data points ordered by time. These data points could be a succession of events from an application's users, the state of CPU and memory usage over time, financial trades recorded every microsecond, or sensors from a car emitting data about the vehicle acceleration and velocity. For that reason, time-series is synonymous with large amounts of data.


Decision-Aware Conditional GANs for Time Series Data

arXiv.org Machine Learning

High fidelity time-series simulators are highly desirable across many domains, either due to a lack of data or because there are high-stakes in regard to the deployment of automated decision methods. A good simulator can improve sample efficiency for training models and be used to evaluate different decision methods. Consider, for example, the use of a simulator for fine-tuning strategies in financial portfolio choice (simulating asset returns) or to support the design of insurance products (simulating risk outcomes). A gap with current GAN-based approaches is that they are not decision-aware, but focus instead on generating the underlying data distribution [KFT19, YJvdS19]. With high fidelity this can support good decisions, but without this, these current methods prove to be insufficient. In a financial portfolio choice problem [Mar52], a risk-neutral portfolio manager will be sensitive to the first order moment of the portfolio return distribution, and cares about mis-specification error in regard to this moment. A risk-sensitive portfolio manager will care more about mis-specification error in regard to the higher moments of the return distribution. Thus, a decision-aware simulator should be designed by tailoring to specific kinds of end users. In capturing a specific kind of decision maker, this requires the simulator to be trained with a loss function that relates to different, decisionrelated quantities.


Multivariate Quantile Bayesian Structural Time Series (MQBSTS) Model

arXiv.org Machine Learning

In this paper, we propose the multivariate quantile Bayesian structural time series (MQB-STS) model for the joint quantile time series forecast, which is the first such model for correlated multivariate time series to the author's best knowledge. The MQBSTS model also enables quantile based feature selection in its regression component where each time series has its own pool of contemporaneous external time series predictors, which is the first time that a fully data-driven quantile feature selection technique applicable to time series data to the author's best knowledge. Different from most machine learning algorithms, the MQBSTS model has very few hyper-parameters to tune, requires small datasets to train, converges fast, and is executable on ordinary personal computers. Extensive examinations on simulated data and empirical data confirmed that the MQBSTS model has superior performance in feature selection, parameter estimation, and forecast.


An analysis of deep neural networks for predicting trends in time series data

arXiv.org Machine Learning

Recently, a hybrid Deep Neural Network (DNN) algorithm, TreNet was proposed for predicting trends in time series data. While TreNet was shown to have superior performance for trend prediction to other DNN and traditional ML approaches, the validation method used did not take into account the sequential nature of time series data sets and did not deal with model update. In this research we replicated the TreNet experiments on the same data sets using a walk-forward validation method and tested our optimal model over multiple independent runs to evaluate model stability. We compared the performance of the hybrid TreNet algorithm, on four data sets to vanilla DNN algorithms that take in point data, and also to traditional ML algorithms. We found that in general TreNet still performs better than the vanilla DNN models, but not on all data sets as reported in the original TreNet study. This study highlights the importance of using an appropriate validation method and evaluating model stability for evaluating and developing machine learning models for trend prediction in time series data.


Practical Financial Data Analysis With Python Data Science

#artificialintelligence

Obtain & Work With Real Financial Data Get Coupon Code Hot & New What you'll learn LEARN To Obtain Real World Financial Data FREE From Yahoo and Quandl BE ABLE To Read In, Pre-process & Visualize Time Series Data IMPLEMENT Common Data Processing And Visualisation Techniques For Financial Data in Python LEARN How To Use Different Python-based Packages For Financial Analysis MODEL Time Series Data To Forecast Future Values With Classical Time Series Techniques USE Machine Learning Regression For Building Predictive Models of Stock prices LEARN How to Use Facebook's Powerful Prophet Algorithm For Modelling Financial Data IMPLEMENT Deep learning methods such as LSTM For Forecasting Stock Data Requirements Prior Familiarity With The Interface Of Jupiter Notebooks and Package Installation Prior Exposure to Basic Statistical Techniques (Such As p-Values, Mean, Variance) Be Able To Carry Out Data Reading And Pre-Processing Tasks Such As Data Cleaning In Python Interest In Working With Time Series Data Or Data With A Time Component To Them Description THIS IS YOUR COMPLETE GUIDE TO FINANCIAL DATA ANALYSIS IN PYTHON! This course is your complete guide to analyzing real-world financial data using Python. All the main aspects of analyzing financial data- statistics, data visualization, time series analysis and machine learning will be covered in depth. If you take this course, you can do away with taking other courses or buying books on Python-based data analysis. In this age of big data, companies across the globe use Python to sift through the avalanche of information at their disposal.


Preparing data for time series analysis

#artificialintelligence

TS may look like a simple data object and easy to deal with, but the reality is that for someone new it can be a daunting task just to prepare the dataset before the actual fun stuff can begin. Every single time series (TS) data is loaded with information; and time series analysis (TSA) is the process of unpacking all of that. However, to unlock this potential, data needs to be prepared and formatted appropriately before putting it through the analytics pipeline. TS may look like a simple data object and easy to deal with, but the reality is that for someone new it can be a daunting task just to prepare the dataset before the actual fun stuff can begin. So in this article we will talk about some simple tips and tricks for getting the analysis-ready data to potentially save many hours of one's productive time.


Time Series Analysis & Predictive Modeling Using Supervised Machine Learning

#artificialintelligence

Time-Series involves temporal datasets that change over a period of time and time-based attributes are of paramount importance in these datasets. The trading prices of stocks change constantly over time, and reflect various unmeasured factors such as market confidence, external influences, and other driving forces that may be hard to identify or measure. There are hypothesis like the Efficient Market Hypothesis, which says that it is almost impossible to beat the market consistently and there are others which disagree with it. Forecasting the future value of a given stock is a crucial task as investing in stock market involves higher risk.. Here, given the historical daily close price for Dow-Jones Index, we would like to prepare and compare forecasting models. The black swan theory, which predicts that anomalous events, such as a stock market crash, are much more likely to occur than would be predicted by the normal distribution.


Time Series Prediction with TensorFlow

#artificialintelligence

In this article, we focus on'Time Series Data' which is a part of Sequence models. In this article, we focus on'Time Series Data' which is a part of Sequence models. In essence, this represents a type of data that changes over time such as the weather of a particular place, the trend of behaviour of a group of people, the rate of change of data, the movement of body in a 2D or 3D space or the closing price for a particular stock in the markets. Analysis of time series data can be done for anything that has a'time' factor involved in it. So what can machine learning help us achieve over time series data? It can also be used to predict missing values in the data. There are certain keywords that always come up when dealing with time series data.


Conditional Sig-Wasserstein GANs for Time Series Generation

arXiv.org Machine Learning

Generative adversarial networks (GANs) have been extremely successful in generating samples, from seemingly high dimensional probability measures. However, these methods struggle to capture the temporal dependence of joint probability distributions induced by time-series data. Furthermore, long time-series data streams hugely increase the dimension of the target space, which may render generative modeling infeasible. To overcome these challenges, we integrate GANs with mathematically principled and efficient path feature extraction called the signature of a path. The signature of a path is a graded sequence of statistics that provides a universal description for a stream of data, and its expected value characterizes the law of the time-series model. In particular, we a develop new metric, (conditional) Sig-$W_1$, that captures the (conditional) joint law of time series models, and use it as a discriminator. The signature feature space enables the explicit representation of the proposed discriminators which alleviates the need for expensive training. Furthermore, we develop a novel generator, called the conditional AR-FNN, which is designed to capture the temporal dependence of time series and can be efficiently trained. We validate our method on both synthetic and empirical datasets and observe that our method consistently and significantly outperforms state-of-the-art benchmarks with respect to measures of similarity and predictive ability.