Manoochehr Ghiassi | Santa Clara University (original) (raw)

Papers by Manoochehr Ghiassi

International Journal of Public Administration in the Digital Age, 2021

Accurate estimate of public expenditures is needed for budgetary planning and government decision... more Accurate estimate of public expenditures is needed for budgetary planning and government decision making. Recent advances in machine learning offers the opportunity for modeling such problems. The paper introduces a novel modeling approach using a machine learning tool to forecast public expenditures and compare and contrast the effectiveness of this approach to traditional modeling alternatives. This research uses historical quarterly data from 1960-2016 to model public expenditures. Various accuracy measures (MAD, MAPE, and RSME) show that the machine learning model is the best alternative formulation and offers 97% forecasting accuracy. This model allows government decision makers to assess alternative policies with specific budgetary impacts. Furthermore, the study also shows that population aging is an important predictor of public expenditures; suggesting that demographic monitoring is indispensable for efficient fiscal planning and management in South Africa.

Computers & Industrial Engineering, 2022

Expert Systems with Applications, 2015

The production of a motion picture is an expensive, risky endeavor. During the five-year period f... more The production of a motion picture is an expensive, risky endeavor. During the five-year period from 2008 through 2012, approximately 90 films were released in the United States with production budgets in excess of $100 million. The majority of these films failed to recoup their production costs via gross domestic box office revenues. Existing decision support systems for pre-production analysis and greenlighting decisions lack sufficient accuracy to meaningfully assist decision makers in the film industry. Established models focus primarily upon post-release and post-production forecasts. These models often rely upon opening weekend data and are reasonably accurate but only if data up until the moment of release is included. A forecast made immediately prior to the debut of a film, however, is of limited value to stakeholders because it can only influence late-stage adjustments to advertising or distribution strategies and little else. In this paper we present the development of a model based upon a Dynamic Artificial Neural Network (DAN2) for the forecasting of movie revenues during the pre-production period. We first demonstrate the effectiveness of DAN2 and show that DAN2 improves box-office revenue forecasting accuracy by 32.8% over existing models. Subsequently, we offer an alternative modeling strategy by adding production budgets, pre-release advertising expenditures, runtime, and seasonality to the predictive variables. This alternative model produces excellent forecasting accuracy values of 94.1%.

Expert Systems with Applications, 2015

The production of a motion picture is an expensive, risky endeavor. During the five-year period f... more The production of a motion picture is an expensive, risky endeavor. During the five-year period from 2008 through 2012, approximately 90 films were released in the United States with production budgets in excess of $100 million. The majority of these films failed to recoup their production costs via gross domestic box office revenues. Existing decision support systems for pre-production analysis and greenlighting decisions lack sufficient accuracy to meaningfully assist decision makers in the film industry. Established models focus primarily upon post-release and post-production forecasts. These models often rely upon opening weekend data and are reasonably accurate but only if data up until the moment of release is included. A forecast made immediately prior to the debut of a film, however, is of limited value to stakeholders because it can only influence late-stage adjustments to advertising or distribution strategies and little else. In this paper we present the development of a model based upon a Dynamic Artificial Neural Network (DAN2) for the forecasting of movie revenues during the pre-production period. We first demonstrate the effectiveness of DAN2 and show that DAN2 improves box-office revenue forecasting accuracy by 32.8% over existing models. Subsequently, we offer an alternative modeling strategy by adding production budgets, pre-release advertising expenditures, runtime, and seasonality to the predictive variables. This alternative model produces excellent forecasting accuracy values of 94.1%.

Neurocomputing, 2005

Artificial neural networks (ANN), have shown to be an effective, general-purpose approach for pat... more Artificial neural networks (ANN), have shown to be an effective, general-purpose approach for pattern recognition, classification, clustering, and prediction. Traditional research in this area uses a network with a sequential iterative learning process based on the feed-forward, back-propagation algorithm. In this paper, we introduce a model that uses a different architecture compared to the traditional neural network, to capture and

Computers & Industrial Engineering, 2003

... should: • Reduce time-to-market for product development, enhancement, and customization ... T... more ... should: • Reduce time-to-market for product development, enhancement, and customization ... This paradigm requires: • Collaborative supply chain partners with synchronized operations, trusted business ... environment and how raw material, products, and information flow through ...

Computers & Industrial Engineering, 2009

This paper presents the development of a dynamic architecture for artificial neural network (DAN2... more This paper presents the development of a dynamic architecture for artificial neural network (DAN2) model for solving nonlinear forecasting and pattern recognition problems. DAN2 is a data driven, feed forward, multilayer, dynamic architecture that is based on the principle of learning and accumulating knowledge at each layer and propagating and adjusting this knowledge forward to the next layer. Model building is automatically and dynamically repeated until a model that accurately captures the behavior of the process is determined. The resulting model is then used to forecast future values. To assess DAN2's effectiveness, we present forecasting results for a variety of nonlinear processes that have been extensively studied in the literature and report comparative results. The set of nonlinear processes considered covers most nonlinear formulations facing researchers. We show DAN2 to be more accurate and to perform consistently better than alternative approaches employed in forecasting nonlinear processes.

Agricultural Systems, 1993

Abstract The three Multiple Criteria Decision Making (MCDM) techniques: goal programming (GP), mu... more Abstract The three Multiple Criteria Decision Making (MCDM) techniques: goal programming (GP), multi-objective programming (MOP) and compromise programming (CP) are discussed in terms of their usefulness for practical farm planning. Application of these methods is illustrated by using the example of a University farm in the UK. The model is of a modest size consisting of 8 constraints and 9 activities and incorporates different objectives. These objectives include: maximization of total gross margin; maximization of permanent labour utilization; minimization of hiring of labour; minimization of annual total variable costs; and, maximization of business trading surplus. Solutions obtained by each method are compared and commented upon with regard to their relative merits in farm planning.

The Computer Journal, 1994

The Computer Journal, 1994

2020 47th IEEE Photovoltaic Specialists Conference (PVSC), 2020

Very large area requirements are one of the key limiting aspects of using PV or Photo-thermal (PT... more Very large area requirements are one of the key limiting aspects of using PV or Photo-thermal (PT) panels for sea water desalination. The high energy needs of the desalination process necessitate a large physical footprint of the PV or PT field to supply enough energy to drive the process. Although a solar approach to desalination is worthy of investigation, creative modes of implementation are required. The use of PV in floating installation is increasingly being deployed and there are now numerous case studies showing the viability. This paper presents the cost considerations for desalination driven by solar, the area required, and the potential of using floating solar designs. Key case studies are presented, the best implementations for desalination are listed, and the cost metrics developed. In addition, a brief indication of the use of Artificial Intelligence for optimization of the process is outlined.

The government of South Africa spends a significant portion of its GDP in support of its public p... more The government of South Africa spends a significant portion of its GDP in support of its public policy including heath care (8.79% in 2014) and social grants (3% in 2013/2014 of which 41% accounts for old age grants). Public policy strategies over a 5-year period from 2010/2011 to 2014/2015 has increased by 39%, moving from ZAR 33764billion ($2597 billion) to ZAR 50336billion ($3872 billion). The growth of the old age grants is expected to continue. Accurate forecasting of such expenditures enables policy makers and government planners for better assessment, planning, and the ultimate allocation of funds in support of their decisions. We address this specific objective by developing a set of time series forecasting models which consider governmental expenditure over time and accounts for the aging population in this process. We offer two models: the first one based on ARIMAX and we introduce a second model that uses a Dynamic Architecture for Artificial Neural Network (DAN2). We ass...

Skip to main content: ...

Interesting itemset mining is a fundamental research problem in knowledge management and machine ... more Interesting itemset mining is a fundamental research problem in knowledge management and machine learning. It is intended to identify interesting relations between variables in a database using some measures of interestingness and has a number of applications, including market basket analysis, web usage mining, intrusion detection, and many others. This paper proposes a new interestingness measure, the fault-tolerant tile. That is based on two observations: (1) the length of an itemset can be as important as its frequency; (2) knowledge discovery from real-world datasets calls for fault-tolerant data mining (e.g. extracting fault-tolerant association rules, analyzing noisy datasets). Given a user-defined fault tolerance value, we are interested in finding the maximum/top-k fault-tolerant tiles. Due to the exponential search space of candidate itemsets, both problems are NP-hard. While using some monotonic property to prune search space is a common strategy for interesting itemset mi...

One powerful capability which needs to be better utilized for energy production is the implementa... more One powerful capability which needs to be better utilized for energy production is the implementation of Artificial Intelligence and Machine Learning (AI/ML) to optimize the production and supply. In addition to production optimization of solar generated energy, AI/ML can be used to achieve cost reductions. We have explored the use of AI/ML to optimize the specific production process taking advantage of IoT and using an innovative Neural Net program developed by one of the authors. Further, this AI/ML can be used for the overall solar supply management, taking into account (1) the potential demand, (2) the solar/weather forecast, (3) the component status, (4) the system equipment conditions, etc. to optimize the energy production for targeted use. This ability to use AI/ML can effectively reduce the costs of energy supply by efficiently targeting the supply to the demand. As well, it can enable greater penetration of PV and DER. This paper will describe the following: (1) the key ad...

2016 49th Hawaii International Conference on System Sciences (HICSS)

We present an approach to brand-related Twitter sentiment analysis using feature engineering and ... more We present an approach to brand-related Twitter sentiment analysis using feature engineering and the Dynamic Architecture for Artificial Neural Networks (DAN2). The approach addresses challenges associated with the unique characteristics of the Twitter language, and the recall of mild sentiment expressions that are of interest to brand management practitioners. We demonstrate the effectiveness of the approach on a Starbucks brand-related Twitter data set. The feature engineering produced a final tweet feature representation consisting of only seven dimensions, with greater feature density. Two sets of experiments were conducted in three-class and five-class tweet sentiment classification. We compare the proposed approach to the performances of two state-of-the-art Twitter sentiment analysis systems from the academic and commercial domains. The results indicate that the approach outperforms these state-of-the-art systems in both three-class and five-class tweet sentiment classification by wide margins, with classification accuracies above 80% and excellent recall of mild sentiment tweets.

International Journal of Public Administration in the Digital Age, 2021

Accurate estimate of public expenditures is needed for budgetary planning and government decision... more Accurate estimate of public expenditures is needed for budgetary planning and government decision making. Recent advances in machine learning offers the opportunity for modeling such problems. The paper introduces a novel modeling approach using a machine learning tool to forecast public expenditures and compare and contrast the effectiveness of this approach to traditional modeling alternatives. This research uses historical quarterly data from 1960-2016 to model public expenditures. Various accuracy measures (MAD, MAPE, and RSME) show that the machine learning model is the best alternative formulation and offers 97% forecasting accuracy. This model allows government decision makers to assess alternative policies with specific budgetary impacts. Furthermore, the study also shows that population aging is an important predictor of public expenditures; suggesting that demographic monitoring is indispensable for efficient fiscal planning and management in South Africa.

Computers & Industrial Engineering, 2022

Expert Systems with Applications, 2015

The production of a motion picture is an expensive, risky endeavor. During the five-year period f... more The production of a motion picture is an expensive, risky endeavor. During the five-year period from 2008 through 2012, approximately 90 films were released in the United States with production budgets in excess of $100 million. The majority of these films failed to recoup their production costs via gross domestic box office revenues. Existing decision support systems for pre-production analysis and greenlighting decisions lack sufficient accuracy to meaningfully assist decision makers in the film industry. Established models focus primarily upon post-release and post-production forecasts. These models often rely upon opening weekend data and are reasonably accurate but only if data up until the moment of release is included. A forecast made immediately prior to the debut of a film, however, is of limited value to stakeholders because it can only influence late-stage adjustments to advertising or distribution strategies and little else. In this paper we present the development of a model based upon a Dynamic Artificial Neural Network (DAN2) for the forecasting of movie revenues during the pre-production period. We first demonstrate the effectiveness of DAN2 and show that DAN2 improves box-office revenue forecasting accuracy by 32.8% over existing models. Subsequently, we offer an alternative modeling strategy by adding production budgets, pre-release advertising expenditures, runtime, and seasonality to the predictive variables. This alternative model produces excellent forecasting accuracy values of 94.1%.

Expert Systems with Applications, 2015

The production of a motion picture is an expensive, risky endeavor. During the five-year period f... more The production of a motion picture is an expensive, risky endeavor. During the five-year period from 2008 through 2012, approximately 90 films were released in the United States with production budgets in excess of $100 million. The majority of these films failed to recoup their production costs via gross domestic box office revenues. Existing decision support systems for pre-production analysis and greenlighting decisions lack sufficient accuracy to meaningfully assist decision makers in the film industry. Established models focus primarily upon post-release and post-production forecasts. These models often rely upon opening weekend data and are reasonably accurate but only if data up until the moment of release is included. A forecast made immediately prior to the debut of a film, however, is of limited value to stakeholders because it can only influence late-stage adjustments to advertising or distribution strategies and little else. In this paper we present the development of a model based upon a Dynamic Artificial Neural Network (DAN2) for the forecasting of movie revenues during the pre-production period. We first demonstrate the effectiveness of DAN2 and show that DAN2 improves box-office revenue forecasting accuracy by 32.8% over existing models. Subsequently, we offer an alternative modeling strategy by adding production budgets, pre-release advertising expenditures, runtime, and seasonality to the predictive variables. This alternative model produces excellent forecasting accuracy values of 94.1%.

Neurocomputing, 2005

Artificial neural networks (ANN), have shown to be an effective, general-purpose approach for pat... more Artificial neural networks (ANN), have shown to be an effective, general-purpose approach for pattern recognition, classification, clustering, and prediction. Traditional research in this area uses a network with a sequential iterative learning process based on the feed-forward, back-propagation algorithm. In this paper, we introduce a model that uses a different architecture compared to the traditional neural network, to capture and

Computers & Industrial Engineering, 2003

... should: • Reduce time-to-market for product development, enhancement, and customization ... T... more ... should: • Reduce time-to-market for product development, enhancement, and customization ... This paradigm requires: • Collaborative supply chain partners with synchronized operations, trusted business ... environment and how raw material, products, and information flow through ...

Computers & Industrial Engineering, 2009

This paper presents the development of a dynamic architecture for artificial neural network (DAN2... more This paper presents the development of a dynamic architecture for artificial neural network (DAN2) model for solving nonlinear forecasting and pattern recognition problems. DAN2 is a data driven, feed forward, multilayer, dynamic architecture that is based on the principle of learning and accumulating knowledge at each layer and propagating and adjusting this knowledge forward to the next layer. Model building is automatically and dynamically repeated until a model that accurately captures the behavior of the process is determined. The resulting model is then used to forecast future values. To assess DAN2's effectiveness, we present forecasting results for a variety of nonlinear processes that have been extensively studied in the literature and report comparative results. The set of nonlinear processes considered covers most nonlinear formulations facing researchers. We show DAN2 to be more accurate and to perform consistently better than alternative approaches employed in forecasting nonlinear processes.

Agricultural Systems, 1993

Abstract The three Multiple Criteria Decision Making (MCDM) techniques: goal programming (GP), mu... more Abstract The three Multiple Criteria Decision Making (MCDM) techniques: goal programming (GP), multi-objective programming (MOP) and compromise programming (CP) are discussed in terms of their usefulness for practical farm planning. Application of these methods is illustrated by using the example of a University farm in the UK. The model is of a modest size consisting of 8 constraints and 9 activities and incorporates different objectives. These objectives include: maximization of total gross margin; maximization of permanent labour utilization; minimization of hiring of labour; minimization of annual total variable costs; and, maximization of business trading surplus. Solutions obtained by each method are compared and commented upon with regard to their relative merits in farm planning.

The Computer Journal, 1994

The Computer Journal, 1994

2020 47th IEEE Photovoltaic Specialists Conference (PVSC), 2020

Very large area requirements are one of the key limiting aspects of using PV or Photo-thermal (PT... more Very large area requirements are one of the key limiting aspects of using PV or Photo-thermal (PT) panels for sea water desalination. The high energy needs of the desalination process necessitate a large physical footprint of the PV or PT field to supply enough energy to drive the process. Although a solar approach to desalination is worthy of investigation, creative modes of implementation are required. The use of PV in floating installation is increasingly being deployed and there are now numerous case studies showing the viability. This paper presents the cost considerations for desalination driven by solar, the area required, and the potential of using floating solar designs. Key case studies are presented, the best implementations for desalination are listed, and the cost metrics developed. In addition, a brief indication of the use of Artificial Intelligence for optimization of the process is outlined.

The government of South Africa spends a significant portion of its GDP in support of its public p... more The government of South Africa spends a significant portion of its GDP in support of its public policy including heath care (8.79% in 2014) and social grants (3% in 2013/2014 of which 41% accounts for old age grants). Public policy strategies over a 5-year period from 2010/2011 to 2014/2015 has increased by 39%, moving from ZAR 33764billion ($2597 billion) to ZAR 50336billion ($3872 billion). The growth of the old age grants is expected to continue. Accurate forecasting of such expenditures enables policy makers and government planners for better assessment, planning, and the ultimate allocation of funds in support of their decisions. We address this specific objective by developing a set of time series forecasting models which consider governmental expenditure over time and accounts for the aging population in this process. We offer two models: the first one based on ARIMAX and we introduce a second model that uses a Dynamic Architecture for Artificial Neural Network (DAN2). We ass...

Skip to main content: ...

Interesting itemset mining is a fundamental research problem in knowledge management and machine ... more Interesting itemset mining is a fundamental research problem in knowledge management and machine learning. It is intended to identify interesting relations between variables in a database using some measures of interestingness and has a number of applications, including market basket analysis, web usage mining, intrusion detection, and many others. This paper proposes a new interestingness measure, the fault-tolerant tile. That is based on two observations: (1) the length of an itemset can be as important as its frequency; (2) knowledge discovery from real-world datasets calls for fault-tolerant data mining (e.g. extracting fault-tolerant association rules, analyzing noisy datasets). Given a user-defined fault tolerance value, we are interested in finding the maximum/top-k fault-tolerant tiles. Due to the exponential search space of candidate itemsets, both problems are NP-hard. While using some monotonic property to prune search space is a common strategy for interesting itemset mi...

One powerful capability which needs to be better utilized for energy production is the implementa... more One powerful capability which needs to be better utilized for energy production is the implementation of Artificial Intelligence and Machine Learning (AI/ML) to optimize the production and supply. In addition to production optimization of solar generated energy, AI/ML can be used to achieve cost reductions. We have explored the use of AI/ML to optimize the specific production process taking advantage of IoT and using an innovative Neural Net program developed by one of the authors. Further, this AI/ML can be used for the overall solar supply management, taking into account (1) the potential demand, (2) the solar/weather forecast, (3) the component status, (4) the system equipment conditions, etc. to optimize the energy production for targeted use. This ability to use AI/ML can effectively reduce the costs of energy supply by efficiently targeting the supply to the demand. As well, it can enable greater penetration of PV and DER. This paper will describe the following: (1) the key ad...

2016 49th Hawaii International Conference on System Sciences (HICSS)

We present an approach to brand-related Twitter sentiment analysis using feature engineering and ... more We present an approach to brand-related Twitter sentiment analysis using feature engineering and the Dynamic Architecture for Artificial Neural Networks (DAN2). The approach addresses challenges associated with the unique characteristics of the Twitter language, and the recall of mild sentiment expressions that are of interest to brand management practitioners. We demonstrate the effectiveness of the approach on a Starbucks brand-related Twitter data set. The feature engineering produced a final tweet feature representation consisting of only seven dimensions, with greater feature density. Two sets of experiments were conducted in three-class and five-class tweet sentiment classification. We compare the proposed approach to the performances of two state-of-the-art Twitter sentiment analysis systems from the academic and commercial domains. The results indicate that the approach outperforms these state-of-the-art systems in both three-class and five-class tweet sentiment classification by wide margins, with classification accuracies above 80% and excellent recall of mild sentiment tweets.