Abstract: This disclosure relates generally to system and method for time series prediction using a sparse recurrent mixture density network (RMDN), such as sparse LSTM-MDN and a sparse ED-MDN, for accurate forecasting of a high variability time series. The disclosed sparse RMDN has the ability to handle high-dimensional input features, capture trend shifts and high variability present in the data, and provide a confidence estimate of the forecast. A high-dimensional time series data is passed through a feedforward layer, which performs dimensionality reduction in an unsupervised manner by inducing sparsity on weights of the feedforward layer. The resultant low-dimensional time series is fed through recurrent layers to capture temporal patterns. These recurrent layers also aid in learning latent representation of the input data. Thereafter, a mixture density network (MDN) is used to model the variability and trend shifts present in the input and it also estimates the confidence of the predictions.

Abstract: Sum of bid quantities (across price bands) placed by generators in energy markets have been observed to be either constant OR varying over a few finite values. Several researches have used simulated data to investigate desired aspect. However, these approaches have not been accurate in prediction. Embodiments of the present disclosure identified two sets of generators which needed specialized methods for regression (i) generators whose total bid quantity (TBQ) was constant (ii) generators whose total bid quantity varied over a few finite values only. In first category, present disclosure used a softmax output based ANN regressor to capture constant total bid quantity nature of targets and a loss function while training to capture error most meaningfully. For second category, system predicts total bid quantity (TBQ) of a generator and then predicts to allocate TBQ predicted across the various price bands which is accomplished by the softmax regression for constant TBQs.

Abstract: In energy markets in which bidding process is used to sell energy, it is important that a mechanism for deciding bidding amount is in place. State of the art systems in this domain have the disadvantage that they rely on simulation data, and also they make certain assumptions, and both the factors can affect accuracy of results when the systems are deployed and are expected to handle practical scenarios. The disclosure herein generally relates to energy markets, and, more particularly, to a method and a system for Reinforcement Learning (RL) based model for generating bids. The system trains a RL agent using historical data with respect to competitor bids places and Market Clearing Prices (MCPs). The RL agent then processes real-time inputs and generates bidding recommendations.

Abstract: This disclosure relates to method and system for optimal policy learning and recommendation for distribution task using deep RL model, in applications where when the action space has a probability simplex structure. The method includes training a RL agent by defining a policy network for learning the optimal policy using a policy gradient (PG) method, where the policy network comprising an artificial neural network (ANN) with a set of outputs. A continuous action space having a continuous probability simplex structure is defined. The learning of the optimal policy is updated based on one of stochastic and deterministic PG. For stochastic PG, a Dirichlet distribution based stochastic policy parameterized by output of the ANN with an activation function at an output layer of the ANN is selected. For deterministic PG, a soft-max function is selected as activation function at the output layer of the ANN to maintain the probability simplex structure.

Abstract: Sum of bid quantities (across price bands) placed by generators in energy markets have been observed to be either constant OR varying over a few finite values. Several researches have used simulated data to investigate desired aspect. However, these approaches have not been accurate in prediction. Embodiments of the present disclosure identified two sets of generators which needed specialized methods for regression (i) generators whose total bid quantity (TBQ) was constant (ii) generators whose total bid quantity varied over a few finite values only. In first category, present disclosure used a softmax output based ANN regressor to capture constant total bid quantity nature of targets and a loss function while training to capture error most meaningfully. For second category, system predicts total bid quantity (TBQ) of a generator and then predicts to allocate TBQ predicted across the various price bands which is accomplished by the softmax regression for constant TBQs.

Abstract: In energy markets in which bidding process is used to sell energy, it is important that a mechanism for deciding bidding amount is in place. State of the art systems in this domain have the disadvantage that they rely on simulation data, and also they make certain assumptions, and both the factors can affect accuracy of results when the systems are deployed and are expected to handle practical scenarios. The disclosure herein generally relates to energy markets, and, more particularly, to a method and a system for Reinforcement Learning (RL) based model for generating bids. The system trains a RL agent using historical data with respect to competitor bids places and Market Clearing Prices (MCPs). The RL agent then processes real-time inputs and generates bidding recommendations.

Abstract: This disclosure relates generally to system and method for time series prediction using a sparse recurrent mixture density network (RMDN), such as sparse LSTM-MDN and a sparse ED-MDN, for accurate forecasting of a high variability time series. The disclosed sparse RMDN has the ability to handle high-dimensional input features, capture trend shifts and high variability present in the data, and provide a confidence estimate of the forecast. A high-dimensional time series data is passed through a feedforward layer, which performs dimensionality reduction in an unsupervised manner by inducing sparsity on weights of the feedforward layer. The resultant low-dimensional time series is fed through recurrent layers to capture temporal patterns. These recurrent layers also aid in learning latent representation of the input data. Thereafter, a mixture density network (MDN) is used to model the variability and trend shifts present in the input and it also estimates the confidence of the predictions.

Abstract: A trading position evaluation system for evaluating trading positions that are globally optimum in market measure includes a trading parameters determination module to determine at a trading time instance from amongst a plurality of trading time instances obtained from a trader, a plurality of trading parameters pertaining to a path-dependent Asian option based on ECC data and market data, retrieved from a database. The trading parameters are indicative of information relating to the path-dependent Asian option. Based on the trading parameters, a position evaluation module evaluates a trading position in the underlying asset at the trading time instance based on the plurality of trading parameters to minimize global variance of profit and loss to the trader.

Abstract: A trading position evaluation system for evaluating trading positions that are globally optimum in market measure includes a trading parameters determination module to determine at a trading time instance from amongst a plurality of trading time instances obtained from a trader, a plurality of trading parameters pertaining to a path-independent European Contingent Claim (ECC) based on ECC data and market data, retrieved from a database. The trading parameters are indicative of information relating to the path-independent ECC. Based on the trading parameters, a position evaluation module evaluates a trading position in the underlying asset at the trading time instance based on the plurality of trading parameters to minimize global variance of profit and loss to the trader.

Abstract: A trading position evaluation system for evaluating trading positions that are globally optimum for a path-dependent European Contingent Claims (ECC) includes an option price determination module configured to determine a current option price and a shifted option price of the path-dependent ECC based on ECC data and market data. The current option price and the shifted option price are determined at a trading time instance, selected from amongst a plurality of trading time instances obtained from a trader, based on at least one discrete-monitoring time instance occurring before the trading time instance. Based on the current option price and the shifted option price, a position evaluation module evaluates a trading position in an underlying asset of the path-dependent ECC at the trading time instance that minimizes global variance of profit and loss to the trader.

Abstract: A trading position evaluation system for evaluating trading positions that are globally optimum for a path-independent multi-asset European Contingent Claim (ECC) includes an option price determination module configured to determine a current option price matrix, a shifted option price matrix, and a normalized conditional variance matrix associated with underlying assets of the ECC at a trading time instance amongst a plurality of trading time instances obtained from a trader, based on ECC data and market data. Based on the current option price matrix, the shifted option price matrix, and the normalized conditional variance matrix, a position evaluation module evaluates a trading position in each of the underlying assets at the trading time instance that minimizes global variance of profit and loss to the trader.

Abstract: A trading position evaluation system for evaluating trading positions that are locally optimum in a market measure includes an option price determination module configured to determine at a trading time instance amongst a plurality of trading time instances obtained from a trader, a scaled option price and a shifted scaled option price of an underlying asset of a European Contingent Claim (ECC) based on ECC data and market data. The ECC data comprises data associated with the ECC and the underlying asset of the ECC, and the market data comprises annualized rate of return and annualized volatility of the underlying asset, and interest rate of market. Based on the scaled option price and the shifted scaled option price, a position evaluation module evaluates a trading position at the trading time instance that minimizes local variance of profit and loss to the trader.

Abstract: A trading position evaluation system for evaluating trading positions that are globally optimum in a risk-neutral measure includes an option price determination module configured to determine a current option price and a shifted option price of an underlying asset of a European Contingent Claim (ECC) at a trading time instance amongst a plurality of trading time instances obtained from a trader, based on ECC data and market data. The ECC data comprises data associated with the ECC and the underlying asset of the ECC, and the market data comprises annualized volatility of the underlying asset and risk-free interest rate of market. Based on the current option price and the shifted option price, a position evaluation module evaluates a trading position at the trading time instance that minimizes global variance of profit and loss to the trader.