A large number of time series forecasting models including traditional statistical models, machine learning models and more recently deep learning have been proposed in the literature. However, choosing the right model along with good parameter values that performs well on a given data is still challenging. Automatically providing a good set of models to users for a given dataset saves both time and effort from using trial-and-error approaches with a wide variety of available models along with parameter optimization. We present AutoAI for Time Series Forecasting (AutoAI-TS) that provides users with a zero configuration (zero-conf) system to efficiently train, optimize and choose best forecasting model among various classes of models for the given dataset. With its flexible zero-conf design, AutoAI-TS automatically performs all the data preparation, model creation, parameter optimization, training and model selection for users and provides a trained model that is ready to use. For given data, AutoAI-TS utilizes a wide variety of models including classical statistical models, Machine Learning (ML) models, statistical-ML hybrid models and deep learning models along with various transformations to create forecasting pipelines. It then evaluates and ranks pipelines using the proposed T-Daub mechanism to choose the best pipeline. The paper describe in detail all the technical aspects of AutoAI-TS along with extensive benchmarking on a variety of real world data sets for various use-cases. Benchmark results show that AutoAI-TS, with no manual configuration from the user, automatically trains and selects pipelines that on average outperform existing state-of-the-art time series forecasting toolkits.

A large number of time series forecasting models including traditional statistical models, machine learning models and more recently deep learning have been proposed in the literature. However, choosing the right model along with good parameter values that performs well on a given data is still challenging. Automatically providing a good set of models to users for a given dataset saves both time and effort from using trial-and-error approaches with a wide variety of available models along with parameter optimization. We present AutoAI for Time Series Forecasting (AutoAI-TS) that provides users with a zero configuration (zero-conf ) system to efficiently train, optimize and choose best forecasting model among various classes of models for the given dataset. With its flexible zero-conf design, AutoAI-TS automatically performs all the data preparation, model creation, parameter optimization, training and model selection for users and provides a trained model that is ready to use. For given data, AutoAI-TS utilizes a wide variety of models including classical statistical models, Machine Learning (ML) models, statistical-ML hybrid models and deep learning models along with various transformations to create forecasting pipelines. It then evaluates and ranks pipelines using the proposed T-Daub mechanism to choose the best pipeline. The paper describe in detail all the technical aspects of AutoAI-TS along with extensive benchmarking on a variety of real world data sets for various use-cases. Benchmark results show that AutoAI-TS, with no manual configuration from the user, automatically trains and selects pipelines that on average outperform existing state-of-the-art time series forecasting toolkits.

In situ and remotely sensed observations have potential to facilitate data-driven predictive models for oceanography. A suite of machine learning models, including regression, decision tree and deep learning approaches were developed to estimate sea surface temperatures (SST). Training data consisted of satellite-derived SST and atmospheric data from The Weather Company. Models were evaluated in terms of accuracy and computational complexity. Predictive skill were assessed against observations and a state-of-the-art, physics-based model from the European Centre for Medium Weather Forecasting. Results demonstrated that by combining automated feature engineering with machine-learning approaches, accuracy comparable to existing state-of-the-art can be achieved. Models captured seasonal patterns in the data and qualitatively reproduce short-term variations driven by atmospheric forcing. Further, it demonstrated that machine-learning-based approaches can be used as transportable prediction tools for ocean variables - the data-driven nature of the approach naturally integrates with automatic deployment frameworks, where model deployments are guided by data rather than user-para-metrisation and expertise. The low computational cost of inference makes the approach particularly attractive for edge-based computing where predictive models could be deployed on low-power devices in the marine environment.

Understanding prospective clients becomes increasingly important as companies aim to enlarge their market bases. Traditional approaches typically treat each client in isolation, either studying its interactions or similarities with existing clients. We propose the Client Network, which considers the entire client ecosystem to predict the success of sale pitches for targeted clients by complex network analysis. It combines a novel ranking algorithm with data visualization and navigation. Based on historical interaction data between companies and clients, the Client Network leverages organizational connectivity to locate the optimal paths to prospective clients. The user interface supports exploring the client ecosystem and performing sales-essential tasks. Our experiments and user interviews demonstrate the effectiveness of the Client Network and its success in supporting sellers' day-to-day tasks.

Selecting an appropriate Autoregressive Moving Average (ARMA) model for a given time series is a classic problem in statistics that is encountered in many applications. Typically this involves a human-in-the-loop and repeated parameter evaluation of candidate models, which is not ideal for learning at scale. We propose a Long Short Term Memory (LSTM) classification model for automatic ARMA model selection. Our numerical experiments show that the proposed method is fast and provides better accuracy than the traditional Box-Jenkins approach based on autocorrelations and model selection criterion. We demonstrate the application of our approach with a case study on volatility prediction of daily stock prices.

A large-scale ensemble prediction model to predict train delays is presented. The ensemble model uses a disparate set of models, two statistical and one simulation-based to generate forecasts of train delays. The first statistical model is a context-aware random forest that accounts for network traffic states, such as likely stretch conflicts and current headway's, exogenous weather, event, and work zone information. The second model is a kernel regression that captures train-specific dynamics. A mesoscopic simulation model that accounts for travel and dwell time variations as well as inferred track occupation conflicts, train connections and rolling stock rotations, is additionally considered. The models have been used in a proof of concept to forecast delays for nationwide passenger services network of Deutsche Bahn, which operates roughly 25,000 trains daily in Germany. Results demonstrate a 25% improvement potential in forecast correctness (fraction of predictions within one minute) and 50% reduction in root mean squared errors compared to the published schedule. The paper describes the models along with the big data challenges that were addressed in data storage, feature and model building, and computation.

This study investigated an approach to improve the accuracy of computationally lightweight surrogate models by updating forecasts based on historical accuracy relative to sparse observation data. Using a lightweight, ocean-wave forecasting model, we created a large number of model ensembles, with perturbed inputs, for a two-year study period. Forecasts were aggregated using a machine-learning algorithm that combined forecasts from multiple, independent models into a single "best-estimate" prediction of the true state. The framework was applied to a case-study site in Monterey Bay, California. A~learning-aggregation technique used historical observations and model forecasts to calculate a weight for each ensemble member. Weighted ensemble predictions were compared to measured wave conditions to evaluate performance against present state-of-the-art. Finally, we discussed how this framework, which integrates ensemble aggregations and surrogate models, can be used to improve forecasting systems and further enable scientific process studies.

We present Route Selection Model (RSM), an online data-driven sales route selector to help firms decide on how to respond to new business opportunities. The system addresses sales route selection (also known as sales channel selection) to determine if the opportunity can be handled by business partners, within the firm using sales agents on the field, or aim to close remotely using digital sellers. Given a new opportunity, RSM recommends an optimal sales route with the highest win probability predicted by machine learning models and provides explanation by meaningful clauses. Compared to the traditional manual passing approach based on business rules, RSM makes faster and more objective recommendations. Our pilot evaluation study shows our recommendations are not only accurate but also interpretable, which is crucial in business decision making. The main features of RSM are: (1) automatically merges multiple sales databases and produce timely recommendations, (2) allows users to navigate through the opportunity information and evidence which supports the recommendation. In this paper we describe the methodology and demonstrate the main functions of RSM.

Search techniques, such as Monte Carlo Tree Search (MCTS) and Proof-Number Search (PNS), are effective in playing and solving games. However, the understanding of their performance in industrial applications is still limited. We investigate MCTS and Depth-First Proof-Number (DFPN) Search, a PNS variant, in the domain of Retrosynthetic Analysis (RA). We find that DFPN's strengths, that justify its success in games, have limited value in RA, and that an enhanced MCTS variant by Segler et al. significantly outperforms DFPN. We address this disadvantage of DFPN in RA with a novel approach to combine DFPN with Heuristic Edge Initialization. Our new search algorithm DFPN-E outperforms the enhanced MCTS in search time by a factor of 3 on average, with comparable success rates.

We demonstrate Castor, a cloud-based system for contextual IoT time series data and model management at scale. Castor is designed to assist Data Scientists in (a) exploring and retrieving all relevant time series and contextual information that is required for their predictive modelling tasks; (b) seamlessly storing and deploying their predictive models in a cloud production environment; (c) monitoring the performance of all predictive models in productions and (semi-)automatically retraining them in case of performance deterioration. The main features of Castor are: (1) an efficient pipeline for ingesting IoT time series data in real time; (2) a scalable, hybrid data management service for both time series and contextual data; (3) a versatile semantic model for contextual information which can be easily adopted to different application domains; (4) an abstract framework for developing and storing predictive models in R or Python; (5) deployment services which automatically train and/or score predictive models upon user-defined conditions. We demonstrate Castor for a real-world Smart Grid use case and discuss how it can be adopted to other application domains such as Smart Buildings, Telecommunication, Retail or Manufacturing.

The detection and diagnosis of abnormal building behavior is key to further improve the comfort and energy efficiency in buildings. An increasing number of sensors can be utilized for this task but these lead to higher integration effort and the need to capture the sensor interactions. This paper presents a novel diagnostic approach for buildings with complex heating, ventilation, airconditioning (HVAC) systems. It uses semantic graphs to automatically create the diagnostic model from the building's data points and to identify potential cause-effectrelationships based on past and current time series data. The approach is validated on various simulated examples of a multiroom HVAC control system. The experimental results show that it can diagnose multiple faults with and without delays with high accuracy.

Feature engineering is one of the most important and time consuming tasks in predictive analytics projects. It involves understanding domain knowledge and data exploration to discover relevant hand-crafted features from raw data. In this paper, we introduce a system called One Button Machine, or OneBM for short, which automates feature discovery in relational databases. OneBM automatically performs a key activity of data scientists, namely, joining of database tables and applying advanced data transformations to extract useful features from data. We validated OneBM in Kaggle competitions in which OneBM achieved performance as good as top 16% to 24% data scientists in three Kaggle competitions. More importantly, OneBM outperformed the state-of-the-art system in a Kaggle competition in terms of prediction accuracy and ranking on Kaggle leaderboard. The results show that OneBM can be useful for both data scientists and non-experts. It helps data scientists reduce data exploration time allowing them to try and error many ideas in short time. On the other hand, it enables non-experts, who are not familiar with data science, to quickly extract value from their data with a little effort, time and cost.

Multimodal travel is a ubiquitous part of living in a city. The operation of modern urban transportation networks can negatively be impacted by multiple factors, including poor traffic conditions caused by congestion and events on the road. In effect, transportation networks feature many types of uncertainty, such as variations in the arrival times of public transport vehicles. However, current systems for multimodal journey planning assume a deterministic environment, assuming, for example, that the published timetables for public transport vehicle are accurate. Slight errors in the deterministic assumptions can result in lost connections, with a corresponding delay at the arrival. We present Docit, the first multimodal journey advising system that reasons about uncertainty in the network knowledge, creating journey plans optimized on the likelihood of arriving on time. Plans are more reliable, which can improve the user perception about the quality of service. This in turn could lead to an increased adoption of public transportation, helping remove cars from the road and fight congestion in Smarter Cities.

The eective management of a power grid with an increasing share of (distributed) renewables and more and more available data, e.g., coming from smart meters, heavily relies on advanced data analytics such as demand and supply forecasting. In this context, data management is one major challenge in electric grids. Large amount of data from multiple heterogeneous sources require transformations, e.g., spatio-temporal alignment or anomaly detection, to serve data analytics tasks and are often applied on dierent views of the data, e.g., on state, substation or feeder level. In this paper, the progress on the development of an energy data management systems for the electricity grid is presented. The design of the system was inspired by the realworld use case of forecasting short-term energy demand in Vermont, using data from a combination of SCADA, smart meters and weather forecasting services. A general data model addressing the aforementioned challenges and aimed at supporting advanced data analytics is introduced. The proposed data model views a time series as an abstract concept that might represent raw measurements or arbitrary operations. The benets of the system is demonstrated for the design and live update energy demand forecasts.

The most readily accessed and abundant renewable energy sources—wind, hydro, and solar—are weather dependent and are therefore inherently intermittent. Energy demand is also dependent on the weather as well as many other difficult-to-model factors. In fact, there are many uncertainty factors that affect the modeling of both energy demand and renewable energy sources. In this paper, we begin with an overview of several of the underlying changes taking place in the energy industry and then specifically consider the uncertainty inherent in the forecasting of energy demand and wind power. We conclude with a discussion of techniques to integrate energy demand and the renewable energy supply, each with their associated uncertainty factors, in a stochastic environment to enable better informed business decisions.

Managing a reliable, renewable, and affordable power grid is a challenging task because the mix of power generating and consuming devices connected to the network continues to change. Improved forecasts help network operators respond to these changes and make data-driven decisions regarding, e.g., demand response and market operations.A system producing short-term energy forecasts of demand and renewable generation at multiple aggregation levels across the service territory of a distribution utility is presented. The system automates the process of ingesting and curating large amounts of data from multiple sources, such as high-resolution weather forecasts, SCADA (supervisory control and data acquisition) data and, smart meter data. This results in a richer and higher-quality data set which improves accuracy for residual demand forecasts because it enables the use of real-time data and the creation of detailed models for solar energy generation.Results of an operational deployment of the system on the service territory covered by the largest electric distribution utility in Vermont, Green Mountain Power, are presented.

Additive models are regression methods which model the response variable as the sum of univariate transfer functions of the input variables. Key benefits of additive models are their accuracy and interpretability on many real-world tasks. Additive models are however not adapted to problems involving a large number (e.g., hundreds) of input variables, as they are prone to overfitting in addition to losing interpretability. In this paper, we introduce a novel framework for applying additive models to a large number of input variables. The key idea is to reduce the task dimensionality by deriving a small number of new covariates obtained by linear combinations of the inputs, where the linear weights are estimated with regard to the regression problem at hand. The weights are moreover constrained to prevent overfitting and facilitate the interpretation of the derived covariates. We establish identifiability of the proposed model under mild assumptions and present an efficient approximate learning algorithm. Experiments on synthetic and real-world data demonstrate that our approach compares favorably to baseline methods in terms of accuracy, while resulting in models of lower complexity and yielding practical insights into high-dimensional real-world regression tasks. Our framework broadens the applicability of additive models to high-dimensional problems while maintaining their interpretability and potential to provide practical insights.