Incorrect Forecasts Research Articles

Cloud computing-based framework for heart disease classification using quantum machine learning approach

Abstract Accurate early identification and treatment of cardiovascular diseases can prevent heart failure problems and reduce mortality rates. This study aims to use quantum learning to predict heart problems to increase the accuracy of traditional prediction and classification methods. Machine learning (ML) and deep learning (DL) techniques need quantum learning to quickly and accurately analyze massive volumes of complex data. With quantum computing, the suggested DL and ML algorithms can change their predictions on the basis of changes in the dataset. This approach could help with the early and accurate detection of chronic diseases. The Cleveland heart disease dataset is undergoing preliminary processing to validate missing values to increase the precision rate and prevent incorrect forecasts. This study examined the feasibility of employing and deploying a quantum ML (QML) framework via cloud computing to categorize cardiac conditions. The research was divided into four sections. First, the principal component analysis was used to preprocess the Cleveland dataset, recursive feature elimination was used to select features, and min–max normalization was used to give the dataset a high-dimensional value. Second, we compared traditional classifiers, such as support vector machine (SVM) and artificial neural network, with the quantum approach to verify the quantum approach’s efficiency. Third, we examined two unique QML classification methods: quantum neural networks (QNNs) and quantum SVM (QSVM). Fourth, bagging-QSVM was developed and deployed as an ensemble learning model. Experimental results using the QNN show an accuracy of 77%, a precision of 76%, a recall of 73%, and an F1 score of 75%. With an accuracy of 85%, a precision of 79%, a recall of 90%, and an F1-score of 84%, the QSVM method demonstrated a much better performance than the QNN. Particularly, the Bagging_QSVM model exhibited an outstanding performance, with a flawless score of 100% across all critical performance measures. The study shows that the bagging method for ensemble learning is a solid way of increasing the accuracy of quantum method predictions.

The Fourth Cervical Vertebra Anterior and Posterior Body Height Projections (Vba) for the Assessment of Pubertal Growth Spurt

This paper aims to propose a statistical model to assess pubertal growth spurt using the ratio of the anterior height projection to the posterior (Vba) of the fourth cervical vertebra body (C4) on cephalograms and to calculate the residual proportion of skeletal maturation and the time for the pubertal growth spurt to end for a given Vba. A sample of 538 cephalograms from healthy-living children aged between 5 and 15 years was analyzed. A segmented regression model was used to explain the different Vba stages relative to the pubertal growth spurt. In addition, the time to achieve skeletal maturation was evaluated for a given Vba between the beginning (Vba1) and the end (Vba2) of the pubertal growth spurt. A longitudinal sample of 25 males and 25 females was analyzed to validate the proposed method. The values of Vba corresponding to higher pubertal development rate ranged from Vba1 = 0.677 (95%CI, 0.644–0.711) to Vba2 = 0.966 (95%CI, 0.905–1.028) and from Vba1 = 0.669 (95%CI, 0.645–0.693) to Vba2 = 1.073 (95%CI, 1.044–1.101) in males and females, respectively. The validation process results showed that our model did not produce any incorrect forecasts. The proposed method estimates the beginning and the end of the pubertal growth spurt together with the residual proportion of skeletal maturation for a given Vba.

Fund Concentration: A Magnifier of Manager Skill

Investors who believe an active manager has insights or forecasts with the potential to earn higher relative returns may look for the manager to concentrate their portfolios. Because foresight is imperfect and correct forecasts will lead to more favorable outcomes and incorrect forecasts to less favorable outcomes, this analysis seeks to explore the impact of decisions to increase concentration on performance. We used portfolio sorts, standard OLS regression methods, and quantile regression methods to test the effect of portfolio concentration in various ways. We found that concentration has a significant convex relationship with the absolute value of relative returns. That is, as the effective number of holdings increases, its association with positive and negative relative performance diminishes. Additionally, we find that increasing concentration has a pronounced positive impact on performance for outperforming funds; the opposite is true for underperforming funds. Most importantly, higher levels of concentration generally hurt the poorly performing funds more than it helps the outperforming funds. For investors and gatekeepers who focus on holdings-based measures of concentration, the findings show that you can’t just look at holdings-based measures of concentration without considering industry exposures.

Venice Keeps Adriatic at Bay [Engineering flood defence

Hydraulics company Enerpac created caissons for three of the four barriers. It developed a damping and levelling control system, with four cylinders at each corner of the caisson and hydraulic accumulators, which absorb forces as the huge structure is placed onto metal sliding plates mounted on concrete mats positioned on the seabed. The control system cushions the momentum caused by lowering the caisson and an algorithm stops residual wave momentum from dislodging the caisson while it is being positioned. A watertight seal between caissons allows a service tunnel for maintenance once the project is complete. Construction work for the MOSE project began in 2003 and was scheduled to be completed in 2011, but delays - from environmental and conservationist challenges as well as bribery and corruption scandals, have resulted in a 10-year slippage and an increase in budget from euro1.6bn to euro5.5bn (around £4.8bn). Raising the gates takes 30 minutes and they remain closed for around four to five hours each time. The barriers have been tested every day since December last year, when they proved effective against high tides of 1.35m. The barriers are raised when there is a forecast of high water above 1.3m. In December 2020, incorrect forecasts of 1.2m-high tides meant that the gates were not raised and 1.37m-high waters flooded parts of the city. At the time, Venice's mayor, Luigi Brugnaro, said that the project is still being tested and that protocols would be developed to activate the defence system sooner. It was activated again shortly afterwards to protect the city from a 1.2m tide the following week. MOSE is scheduled to be fully operational by the end of this year to protect historic buildings and Venetians' businesses from the Adriatic Sea.

Forecasting of Induced Seismicity Rates from Hydraulic Fracturing Activities Using Physics-Based Models for Probabilistic Seismic Hazard Analysis: A Case Study

One of the major challenges in seismic hazard analysis for induced seismicity is the forecasting of future seismicity rates, which are described by the Gutenberg–Richter parameters (a and b-values from the earthquake magnitude frequency distributions). In this study, we implement two methodologies in order to determine the Gutenberg–Richter parameters related to future induced seismicity: the Seismogenic Index and the Hydromechanical Nucleation model. We apply both methods in one recent case of induced seismicity: the Horn River Basin, Northeast B.C., Canada. We perform two tests to compare the predictions of both models with the observed seismicity. First, we compare the predicted number of earthquakes exceeding a certain magnitude per month with the observed number of earthquakes. In this test, both methods predict earthquake rates similar to the observed induced seismicity in the Horn River Basin. Second, we evaluate how appropriate are the predictions for specific magnitude ranges (given by forecasted Gutenberg–Richter parameters). In this case, both models make inaccurate predictions for specific magnitude ranges (annual magnitude frequency distributions), resulting in an under- or overestimation of the hazard but often with contradicting forecasts, despite using shared observations. The predictions under- and overestimate the hazard at different time points, due to the complexity in the evolution of the seismicity, and the assumption of constant b-values. As a result, these incorrect forecasts for future magnitude-frequency distributions lead to biased seismic hazard and ground motion predictions. More research effort is required in order to forecast more accurate Gutenberg–Richter parameters, particularly changes in the b-value, as observed in the Horn River Basin induced seismicity case.

The problem of shelf-warmers in electronic commerce: a proposed solution

This paper presents the significant problem of so called shelf-warmers in the environment of electronic commerce. In the first part of the paper, the factors that have led to an increasing stock of shelf-warmers in online stores are discussed. These factors are divided into two groups: those that occur mainly in an online store environment and those not specifically associated with an online environment. One group of factors are related to the large number of items offered in an online store enabled by various models of inventory management (e.g. drop-shipping, 3PL, 4PL), the lack of a need to maintain costly space for the exposition of goods, the heterogeneity of online shoppers and the large number of returns from customers. The other group of factors concern incorrect forecasts of demand, inappropriate inventory control, choice of product assortment, pricing policies and the end of a product’s life cycle. The problem of appropriately identifying shelf-warmers is then discussed and an index measuring the tendency of a good to be a shelf-warmer is proposed. Based on this, different methods for dealing with shelf-warmers are outlined in the form of the use of recommendation systems, search engine optimization and social media. The paper then presents an experiment conducted in a real business environment to assess the effectiveness of some of the aforementioned methods. This experiment resulted in the sale of approximately 33% of 160 selected shelf-warmers and over 50% from one group (number 8) where all the suggestions were implemented, within a period of 10 months. The results obtained show that the methods and recommendations proposed may help online stores to deal with the problem of shelf-warmers.

Selective exposure partly relies on faulty affective forecasts

People preferentially consume information that aligns with their prior beliefs, contributing to polarization and undermining democracy. Five studies (collective N = 2455) demonstrate that such “selective exposure” partly stems from faulty affective forecasts. Specifically, political partisans systematically overestimate the strength of negative affect that results from exposure to opposing views. In turn, these incorrect forecasts drive information consumption choices. Clinton voters overestimated the negative affect they would experience from watching President Trump’s Inaugural Address (Study 1) and from reading statements written by Trump voters (Study 2). Democrats and Republicans overestimated the negative affect they would experience from listening to speeches by opposing-party senators (Study 3). People’s tendency to underestimate the extent to which they agree with opponents’ views drove the affective forecasting error. Finally, correcting biased affective forecasts reduced selective exposure by 24–34% (Studies 4 and 5).

Amblyomma ticks and future climate: Range contraction due to climate warming

Ticks of the Amblyomma cajennense species complex are important vectors of spotted fever in Latin America. Environmental conditions determine the geographic distribution of ticks, such that climate change could influence the distribution of tick-borne diseases. This study aimed to analyze the potential geographic distribution of A. cajennense complex ticks in a Brazil region under present-day and future climate models, assuming dispersal limitations and non-evolutionary adaptation of these tick populations to climate warming. Records of A. cajennense sensu stricto (s.s.) and Amblyomma sculptum were analyzed. Niche models were calibrated using Maxent considering climate variables for 1950–2000 and projecting models to conditions anticipated for 2050 and 2070 under two models of future climate (CCSM4 and HadGEM2-AO). Broad suitable areas for A. cajennense s.s. and A. sculptum were found in present-day climate models, but suitability was reduced when models were projected to future conditions. Our exploration of future climates showed that broad areas had novel climates not existing currently in the study region, including novel extremely high temperatures. Indeed, predicted suitability in these novel conditions would lead to biologically unrealistic results and therefore incorrect forecasts of future tick-distribution. Previous studies anticipating expansions of vectors populations due to climate change should be considered with caution as they assume that model extrapolation anticipates that species would evolve rapidly for adaptation to novel climatic conditions.

A dynamical climate-driven malaria early warning system evaluated in Uganda, Rwanda and Malawi

Background Malaria is a climate-sensitive disease with a significant socio-economic impact. As monthly and seasonal dynamical climate prediction systems have improved their skill in the tropics over recent years, there is now the potential to use these forecasts to drive dynamical malaria modelling systems to provide early warnings of climate-related transmission hazards in holo and hyper endemic settings. Materials and methods A new pilot dynamical malaria prediction system was introduced. Multiple temperature and precipitation forecasts from the ECMWF monthly and seasonal prediction systems were used to drive the spatially explicit, dynamical malaria model VECTRI that accounts for population density and climate to produce forecasts of up to 4 months ahead. The malaria forecasts were started from realistic initial conditions derived from climate observations. The parameter predicted is the logarithm of the entomological inoculation rate (EIR). Forecasts are made on a grid mesh with a spatial resolution of 25km, but are then aggregated at the administrative district level, and normalized to be evaluated using normalized district level crude incidence data or sentinel site cases (suspected or confirmed) for three countries: Uganda, Rwanda and Malawi. The forecasts are evaluated over a period of approximately a decade, depending on the length of the data record available. Results The results show that for a number of districts in which interventions have been limited over the evaluation period, the forecasts were statistically significantly correlated with observed malaria outcomes, with the forecasts predicting the years of anomalous transmission and the sub-seasonal anomalies well. This was true for districts of both low and higher endemicity. However, for the majority of locations, significance levels were lower. The potential reasons for this are numerous, including incorrect climate forecasts, errors or missing physics (e.g. lack of immunity) in the malaria model, inaccuracies in the cases data itself, and interventions that have reduced prevalence and transmission risk as a function of time. We demonstrate, using confirmed sentinel site data, that data inaccuracies in the district statistics can be significant. Interestingly, the analysis and forecast system appear to indicate that the reduction in malaria prevalence in Rwanda over the past decade has been achieved against a backdrop of increasing transmission hazard due to climate. We conclude by discussing the weaknesses in the system that require addressing and the next steps to pilot this system in an operational context.

Identifying Structural Breaks in Stochastic Mortality Models

In recent years the issue of life expectancy has become of upmost importance to pension providers, insurance companies and the government bodies in the developed world. Significant and consistent improvements in mortality rates and hence life expectancy have led to unprecedented increases in the cost of providing for older ages. This has resulted in an explosion of stochastic mortality models forecasting trends in mortality data in order to anticipate future life expectancy and hence quantify the costs of providing for future ageing populations. Many stochastic models of mortality rates identify linear trends in mortality rates by time, age and cohort and forecast these trends into the future using standard statistical methods. The modeling approaches used fail to capture the effects of any structural change in the trend and thus potentially produce incorrect forecasts of future mortality rates. In this paper we look at a range of leading stochastic models of mortality and test for structural breaks in the trend time series. We find that in almost all cases structural breaks in the time series are present and when allowing for these the resulting forecasts are significantly improved.

Effect of the accuracy of price forecasting on profit in a Price Based Unit Commitment

This paper discusses and quantifies the so-called loss of profit (i.e., the sub-optimality of profit) that can be expected in a Price Based Unit Commitment (PBUC), when incorrect price forecasts are used. For this purpose, a PBUC model has been developed and utilized, using Mixed Integer Linear Programming (MILP). Simulations are used to determine the relationship between the Mean Absolute Percentage Error ( MAPE) of a certain price forecast and the loss of profit, for four different types of power plants. A Combined Cycle (CC) power plant and a pumped storage unit show highest sensitivity to incorrect forecasts. A price forecast with a MAPE of 15%, on average, yields 13.8% and 12.1% profit loss, respectively. A classic thermal power plant (coal fired) and cascade hydro unit are less affected by incorrect forecasts, with only 2.4% and 2.0% profit loss, respectively, at the same price forecast MAPE. This paper further demonstrates that if price forecasts show an average bias (upward or downward), using the MAPE as measure of the price forecast might not be sufficient to quantify profit loss properly. Profit loss in this case has been determined as a function of both shift and MAPE of the price forecast.

Non-Bayesian Learning

A series of experiments suggest that, compared to the Bayesian benchmark, people may either underreact or overreact to new information. We consider a setting where agents repeatedly process new data. Our main result shows a basic distinction between the long-run beliefs of agents who underreact to information and agents who overreact to information. Like Bayesian learners, non-Bayesian updaters who underreact to observations eventually forecast accurately. Hence, underreaction may be a transient phenomenon. Non-Bayesian updaters who overreact to observations eventually forecast accurately with positive probability but may also, with positive probability, converge to incorrect forecasts. Hence, overreaction may have long-run consequences.

International Real Estate Review

This study captures the essential elements of the price expectations of market participants in a rising market. Adopting a forward-looking approach, this paper explores the effectiveness of expectations as an indicator of forthcoming housing price changes in Hong Kong. Examination of the quarterly survey data from December 2003 to September 2007 indicates that both homeowners and non-homeowners tend to overestimate the probability of future housing price increases yet underestimate its volatility. This adds weight to the argument that market participants are generally not rational in the prediction of price movement. Homeowners, investors and potential home buyers have more or less the same level of confidence about the future market outlook. Like non-owners, they expect higher prices. The number of correct forecasts exceeds incorrect forecasts, suggesting that overall price expectations are fairly close to realization. It can be broadly concluded that the aggregate price expectations in the long run can be an appropriate forecasting tool for future market performance.

Session Discussion: Can Land Use Economists Help Planners?

T his session's authors do a wonderful job of providing empirical evidence on the population and employment growth patterns currently reshaping the American landscape. Traditional land use patterns are being replaced by new alternatives in many areas and reverting to old patterns in other places. Suburbs and rural communities are being inundated with lowto medium-density residential development, often considered sprawl by longer term residents. Many American cities are de-densifying, with populations dropping while land coverage increases. On the other hand, a few cities are experiencing rebirth and increased density as inner-cities redevelop with luxury high rises and mixed-use communities. Since these trends will drive infrastructure spending decisions, understanding and predicting them is important. The difficulty in predicting and explaining these trends lies in their genesis: millions of people making individual decisions on where to live, work, send their kids to school, etc. Because of the multiplicity of factors inherent in our decisions about lifestyle choices, explaining such decisions with statistical precision is an incredibly difficult task. However, attempts must be made because government officials need guidance in allocating budgets for new roads, schools, water treatment plants, and all the other capital investments that support our modern lifestyle. Incorrect growth forecasts mean billions (or trillions) of tax dollars wasted. The dollar amounts at stake are phenomenal; in 2000, road expenditures alone totaled $127 billion nationwide (U.S. Department of Transportation). Thus, this area of research is of the highest importance. The paper by Partridge et al. looks at where jobs are being created and finds that employment growth in locations near an urban center exceeds that in areas farther away, but the effect is not overwhelming. Further, they find that natural

Is a Detailed Tax Planning for Investment Decisions Worthwhile? Evidence from Germany

Real-world tax systems distort investment and financing decisions. Therefore, taxes are integrated into capital budgeting models. However, these models use very simplified tax bases. Investors typically assume tax bases to be equal to cash flows less depreciation allowances. We analyse the investment incentives resulting from such a simplified tax planning. The analysis is based on a stochastic business simulation model applying empirical data from different industries. Using Monte Carlo simulations, we cover a wide variety of business developments. We show that using cash flows minus depreciation allowances as a tax base generates deviations compared to investment planning with a detailed tax base in accordance with current tax laws. The anticipated NPVs or future values of companies can be too high or too low, depending on the company's legal structure and industry. Using only cash flows as a tax base leads to an anticipated future value which is always too high. But these deviations are small compared to incorrect forecasts of interest rates or tax rates. For example, if the income tax is reduced to 37%, while the anticipated tax rate is 42%, or if the interest rate increases by 3 percent points, the future value and the deviation are much higher compared to tax base-induced deviations. Hence, investors should pay more attention to the forecast of interest rates and tax rates, as opposed to reproducing a more detailed tax base of investment projects.

Intertwined Cultural and Relational Environments of Organizations

I examine fundamental elements of the cultural and relational environments of the organizations that produce electoral forecasts in the Spanish parliamentary elections. The analysis reveals how these elements shape the interests and decisions in a collectivity of organizations that share a common technology. I investigate the reasons for the coincidence of incorrect forecasts across the polling firms by considering neoinstitutional propositions about the social construction of institutions and isomorphism by mimesis. The coincidence of forecasts contributes to preserving the firms' individual and collective social legitimacy despite repeated forecasting failures. To reach coincidence, the firms' decisions about what forecast to present is decoupled from the ineffective technological process that legitimates the forecasts. Cultural conceptions about the production and technology of the forecasting activity generate interdependence among the polling firms. This relational aspect compels firms to conform their forecasts to those of other firms.

Forecasting Peak Daily Ozone Levels: Part 2—A Regression with Time Series Errors Model Having a Principal Component Trigger to Forecast 1999 and 2002 Ozone Levels

A modified time series approach, a Box-Jenkins regression with time series errors (RTSE) model plus a principal component (PC) trigger, has been developed to forecast peak daily 1-hr ozone (O3) in real time at the University of Wisconsin-Milwaukee North (UWM-N) during 1999 and 2002. The PC trigger acts as a predictor variable in the RTSE model. It tries to answer the question: will the next day be a possible high O3 day? To answer this question, three PC trigger rules were developed: (1) Hi-Low Checklist, (2) Discriminant Function Approach I, and (3) Discriminant Function Approach II. Also, a pure RTSE model without including the PC trigger and a persistence approach were tested for comparison. The RTSE model with DFA I successfully forecast the only two 1-hr federal exceedances (124 ppb), one in 1999 and one in 2002. In terms of the O3 100-ppb exceedances, 60–80% of the incorrect forecasts occurred with incorrect PC decisions. A few others may have been caused by unexpected O3- weather relations. When the three approaches used UWM-N data to forecast a 100-ppb exceedance somewhere in the Milwaukee, WI, metropolitan area, their performance was dramatically improved: the false alarm rate was reduced from 0.89 to 0.44, and the probability of detection was increased from 0.71 to 0.88.

Maximising returns on dead assets: How to increase a facility’s reliability and generate revenue

On‐site power has many potential benefits, from temporary relief to congested transmission and distribution systems, to alleviating problems created by incorrect load forecasts, all the way to meeting the load requirements of a facility. Many of these assets are being installed to take advantage of one or more of the above opportunities. This paper shows how effective utilisation of these assets not only increases the reliability of a facility, but also helps generate revenue from assets that would otherwise sit idle. It goes on to demonstrate to facility managers how they can successfully implement such a model through better understanding of their facilities’ needs combined with financial details of various programmes offered by local suppliers of electricity.

Validation of weather and leaf wetness forecasts for a lettuce downy mildew warning system

Leaf wetness and weather forecasts were important inputs in a warning system developed previously for lettuce downy mildew in coastal California. To improve the predictive ability of this warning system, reliability of weather and leaf wetness forecasts were evaluated. Weather forecasts from two commercial companies were compared with weather data measured in or near commercial lettuce fields during 1994-1998, at several different locations in coastal California. Measured leaf wetness data were compared with forecasts by company A. and by a dew simulation model using weather forecasts of company B or measured weather data (except cloud cover) as inputs of the model. When forecast and observed weather data pooled over 24 h were compared, the forecasts appeared to be accurate, but when data were analyzed hourly, forecasts had large errors during early morning hours, which coincided with the critical period for infection by the pathogen. Correspondingly, both company A and the dew simulation model frequently gave incorrect leaf wetness forecasts during morning and evening hours although incorrect forecasts were rare from Pacific standard time 10:00 to 17:00 and 00:00 to 06:00. Weather and leaf wetness forecasts were generally better for the Salinas Valley than for the Santa Maria Valley. The errors in weather forecasts and the innate weaknesses in the dew simulation model might have resulted in the inaccuracy in leaf wetness forecasts. This, in turn, led to errors in warnings of downy mildew infection by the previous system.

A Comparison of Exhaust Condensation Trail Forecast Algorithms at Low Relative Humidity

Abstract The Schrader and Schumann contrail forecast algorithms and a third algorithm are evaluated under low relative humidity conditions using a dataset of asynoptic atmospheric soundings and 318 coincident ground-based aircraft and contrail observations collected near Dayton, Ohio. Aircraft were positively identified and their flight altitudes were determined using either Federal Aviation Administration flight logs or data collected with the Wright–Patterson Air Force Base air traffic control radar. The sounding data were used with assumed aircraft performance parameters to prepare nowcasts of contrail critical temperatures. The nowcasts were examined subjectively by comparing the distribution of correct and incorrect forecasts as a function of the difference between critical temperature and ambient temperature. Objective evaluation against the contrail observations also was done using several common statistical measures. The third algorithm produced critical temperatures that were systematically too c...