In this paper, Deep Learning-based models are used for predicting the number of novel coronavirus (COVID-19) positive reported cases for 32 states and union territories of India Recurrent neural network (RNN) based long-short term memory (LSTM) variants such as Deep LSTM, Convolutional LSTM and Bi-directional LSTM are applied on Indian dataset to predict the number of positive cases LSTM model with minimum error is chosen for predicting daily and weekly cases It is observed that the proposed method yields high accuracy for short term prediction with error less than 3% for daily predictions and less than 8% for weekly predictions Indian states are categorised into different zones based on the spread of positive cases and daily growth rate for easy identification of novel coronavirus hot-spots Preventive measures to reduce the spread in respective zones are also suggested A website is created where the state-wise predictions are updated using the proposed model for authorities,researchers and planners This study can be applied by other countries for predicting COVID-19 cases at the state or national level

Prediction and analysis of COVID-19 positive cases using deep learning models: A descriptive case study of India

Residential load forecasting based on LSTM fusing self-attention mechanism with pooling

COVID-19 virus has encountered people in the world with numerous problems. Given the negative impacts of COVID-19 on all aspects of people's lives, especially health and economy, accurately forecasting the number of cases infected with this virus can help governments to make accurate decisions on the interventions that must be taken. In this study, we propose three hybrid approaches for forecasting COVID-19 time series methods based on combining three deep learning models such as multi-head attention, long short-term memory (LSTM), and convolutional neural network (CNN) with the Bayesian optimization algorithm. All models are designed based on the multiple-output forecasting strategy, which allows the forecasting of the multiple time points. The Bayesian optimization method automatically selects the best hyperparameters for each model and enhances forecasting performance. Using the publicly available epidemical data acquired from Johns Hopkins University's Coronavirus Resource Center, we conducted our experiments and evaluated the proposed models against the benchmark model. The results of experiments exhibit the superiority of the deep learning models over the benchmark model both for short-term forecasting and long-horizon forecasting. In particular, the mean SMAPE of the best deep learning model is 0.25 for the short-term forecasting (10 days ahead). Also, for long-horizon forecasting, the best deep learning model obtains the mean SMAPE of 2.59.

Prediction of COVID-19 Confirmed Cases Combining Deep Learning Methods and Bayesian Optimization.

Efficient anomaly detection and diagnosis in multivariate time-series data is of great importance for modern industrial applications. However, building a system that is able to quickly and accurately pinpoint anomalous observations is a challenging problem. This is due to the lack of anomaly labels, high data volatility and the demands of ultra-low inference times in modern applications. Despite the recent developments of deep learning approaches for anomaly detection, only a few of them can address all of these challenges. In this paper, we propose TranAD, a deep transformer network based anomaly detection and diagnosis model which uses attention-based sequence encoders to swiftly perform inference with the knowledge of the broader temporal trends in the data. TranAD uses focus score-based self-conditioning to enable robust multi-modal feature extraction and adversarial training to gain stability. Additionally, model-agnostic meta learning (MAML) allows us to train the model using limited data. Extensive empirical studies on six publicly available datasets demonstrate that TranAD can outperform state-of-the-art baseline methods in detection and diagnosis performance with data and time-efficient training. Specifically, TranAD increases F1 scores by up to 17%, reducing training times by up to 99% compared to the baselines.

TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data

NILM Applications: Literature review of learning approaches, recent developments and challenges

An optimized model using LSTM network for demand forecasting

In today’s fast moving world of marketing from product-orientation to customer-orientation, the management of customer treatment can be seen as a key to achieve revenue growth and profitability. Knowledge of customer behavior can help marketing managers re-evaluate their strategies with the customers and plan to improve and expand their application of the most effective strategies. B2B or business customers are more complex, their buying process is more complicated and their sales value is greater. The business marketers usually prefer to cooperate with fewer but larger buyers than the final consumer marketer. As a business transaction requires more decision makings and more professional buying effort than the consumer market does, the efficient relationship with business customers is of paramount importance. Most customer segmentation approaches based on customer value fail to account for the factor of time and the trend of value changes in their analysis. In this article, we classify customers based on their value using the RFM model and K-means clustering method. Then, an assessment of changes over several periods of time is carried out. The originality of this research lies in its incorporation of time and trend of customer value changes in improving the accuracy of predictions based on the past behavior of customers. For this purpose, we used the POS customer transactions.

New approach to customer segmentation based on changes in customer value

Data mining and in particular forecasting tools and techniques are being increasingly exploited by businesses to predict customer behavior and to formulate effective marketing programs. Conventionally, customer segmentation approaches are utilized when dealing with a large population of customers. Inspired by this idea, a new methodology is proposed in this study to perform segment-level customer behavior forecasting. To keep the dynamic nature of customer behavior, customer behavior is represented as a time series. Therefore, customer behavior forecasting is changed into a time series forecasting problem. The proposed methodology contains two main components i.e. clustering and forecasting. In the clustering phase, time series are clustered using time series clustering algorithms, and then, in the forecasting phase, the behavior of each segment is predicted via time series forecasting techniques. The main objective is to predict future behavior at segment level. The forecasting component also consists of a combined method exploiting the concept of forecast fusion. The combined method employs a pool of forecasters both from traditional time series forecasting and computational intelligence methods. To test the usefulness of the proposed method, a case study is carried out using the data of customers’ point of sale (POS) in a bank. The results of the experiments demonstrate that the combined method outperforms all other individual forecasters in terms of symmetric mean absolute percentage error (SMAPE). The proposed methodology can be correspondingly applied in other areas and applications of time series forecasting.

A new framework for predicting customer behavior in terms of RFM by considering the temporal aspect based on time series techniques

Financial time-series forecasting is one of the most challenging domains in the field of time-series analysis. This is mostly due to the highly non-stationary and noisy nature of financial time-series data. With progressive efforts of the community to design specialized neural networks incorporating prior domain knowledge, many financial analysis and forecasting problems have been successfully tackled. The temporal attention mechanism is a neural layer design that recently gained popular-ity due to its ability to focus on important temporal events. In this paper, we propose a neural layer based on the ideas of temporal attention and multi-head attention to extend the capability of the underlying neural network in focusing simultaneously on multiple temporal instances. The effectiveness of our approach is validated using large-scale limit-order book market data to forecast the direction of mid-price movements. Our experiments show that the use of multi-head temporal attention modules leads to enhanced prediction performances compared to baseline models.

/pdf/multi-head-temporal-attention-augmented-bilinear-network-for-3ak96xwc.pdf

Multi-head Temporal Attention-Augmented Bilinear Network for Financial time series prediction

The purpose of this paper is to propose a new methodology that handles the issue of the dynamic behavior of customers over time.,A new methodology is presented based on time series clustering to extract dominant behavioral patterns of customers over time. This methodology is implemented using bank customers’ transactions data which are in the form of time series data. The data include the recency (R), frequency (F) and monetary (M) attributes of businesses that are using the point-of-sale (POS) data of a bank. This data were obtained from the data analysis department of the bank.,After carrying out an empirical study on the acquired transaction data of 2,531 business customers that are using POS devices of the bank, the dominant trends of behavior are discovered using the proposed methodology. The obtained trends were analyzed from the marketing viewpoint. Based on the analysis of the monetary attribute, customers were divided into four main segments, including high-value growing customers, middle-value growing customers, prone to churn and churners. For each resulted group of customers with a distinctive trend, effective and practical marketing recommendations were devised to improve the bank relationship with that group. The prone-to-churn segment contains most of the customers; therefore, the bank should conduct interesting promotions to retain this segment.,The discovered trends of customer behavior and proposed marketing recommendations can be helpful for banks in devising segment-specific marketing strategies as they illustrate the dynamic behavior of customers over time. The obtained trends are visualized so that they can be easily interpreted and used by banks. This paper contributes to the literature on customer relationship management (CRM) as the proposed methodology can be effectively applied to different businesses to reveal trends in customer behavior.,In the current business condition, customer behavior is changing continually over time and customers are churning due to the reduced switching costs. Therefore, choosing an effective customer segmentation methodology which can consider the dynamic behaviors of customers is essential for every business. This paper proposes a new methodology to capture customer dynamic behavior using time series clustering on time-ordered data. This is an improvement over previous studies, in which static segmentation approaches have often been adopted. To the best of the authors’ knowledge, this is the first study that combines the recency, frequency, and monetary model and time series clustering to reveal trends in customer behavior.

Mostafa Shabani

Papers

An optimized model using LSTM network for demand forecasting

New approach to customer segmentation based on changes in customer value

A new framework for predicting customer behavior in terms of RFM by considering the temporal aspect based on time series techniques

Multi-head Temporal Attention-Augmented Bilinear Network for Financial time series prediction

A new methodology for customer behavior analysis using time series clustering: A case study on a bank’s customers