The paper improves car leasing pricing by forecasting residual values with asymmetric cost functions.
problem Forecasting residual values for leasing contracts with asymmetric cost functions.
method Develops forecasting models with asymmetric cost functions to address the asymmetric costs of forecast errors.
result Forecasting with asymmetric cost functions reduces decision costs by about 8% compared to standard models.
Article offers models for choosing sale-leaseback vs debt.
problem Choosing between sale-leaseback and debt for commercial real estate.
method Developed decision models for leasing.
result Models can be applied to various types of leasing.
Study values and optimizes forestry leases under risk and uncertainty.
problem Valuing and optimizing forestry leases in the presence of catastrophe risk and parameter uncertainty.
method Stochastic bio-economic models, Kalman filter, maximum likelihood estimation, RBSDEs, Monte Carlo simulations.
result Conservative strategy is recommended due to parameter uncertainty.
A new method prices time-to-event cash flows using survival analysis.
problem Pricing insurance investment portfolios with time-to-event cash flows.
method Discrete-time survival analysis framework, hazard rate estimators, asymptotic multivariate normality.
result Pricing model yields estimates closer to actual cash flows than non-random models.
Proposes a mathematical model for safe and scalable self-driving cars.
problem Ensuring safety and scalability in self-driving cars.
method Introduces Responsibility-Sensitive Safety (RSS) model and scalable design.
result Proposes a mathematical model for safety assurance and scalable design.
A new car following model reduces platoon level traffic errors.
problem Enhance traffic micro-simulation accuracy in platoon level traffic.
method Unidirectional interconnected LSTM model structure and scheduled sampling technique.
result The proposed model reduces errors by almost 40% compared to traditional models.
A car's motion shows flat parabolic geometry.
problem Understanding the geometry of a car's motion.
method Analyzing a car as a nonholonomic system.
result Shows a car's motion as a flat parabolic geometry.
Detects ridesourcing cars from ordinary vehicles using transfer learning.
problem Unauthorized ridesourcing activities impairing the industry.
method Two-stage transfer learning framework: RF for initial labeling, CNN for final detection.
result Achieves similar accuracy to supervised learning methods without labeled data.
A kinematics of the motion of a car is reformulated in terms of the theory of gauge potentials (connection on principal bundle). E(2)-connection originates in the no-slipping contact of the car with a road.
Deep RL model mimics human car-following behavior with high accuracy.
problem Developing autonomous cars that can follow other vehicles like humans.
method Deep reinforcement learning using historical driving data and reward function.
result DDPGvRT model achieves lower validation errors (18% spacing, 5% speed) compared to other models.
Predicting car sales using maximum entropy principle and proportional growth dynamics.
problem Predicting the sales of new cars over time.
method Analyzing 10 years of Spanish car sales data, applying Gibrat's law, and using the Maximum Entropy Principle.
result Car sales distribution follows predictions from the Maximum Entropy Principle for proportional growth systems.
DASC combines social media and car sensors to improve disaster response.
problem Inconsistent reliability and inconsistent availability of human sensors.
method Hybrid social-car sensing system using game theory, feedback control, and MDP.
result DASC improves detection accuracy and efficiency in disaster response.
Reduces car control labels to simplify autonomous driving.
problem Redundant labels in semantic maps hinder efficient autonomous driving.
method Quantifies label importance for car control, simplifies labels.
result Reduced labels improve efficiency and simplify autonomous driving tasks.
Proposes a method for training Bayesian neural networks using synthetic data from Raman and CARS spectra.
problem Limited real observations in Raman and CARS spectroscopy.
method Log-Gaussian Gamma Processes and Bayesian Neural Networks.
result Trained Bayesian neural networks provide accurate estimates of Raman and CARS spectra with uncertainty quantification.
Framework fuses RGB images and depth maps for self-driving car control.
problem Fault tolerance in self-driving cars with sensor failures.
method Deep neural network architecture for sensor fusion.
result Framework can learn to use relevant sensor information even when one fails.
Improved car-hailing service by analyzing POI effects.
problem Minimize passenger waiting time and optimize vehicle utilization.
method Analyzed POI effects on supply-demand gap and proposed a POI selection scheme integrated with XGBoost.
result More accurate and stable estimation results.
RankNet forecasts car racing positions with improved accuracy and stability.
problem Forecasting rank positions in car racing, especially considering pit stops.
method Cause-effect decomposition in RankNet, incorporating probabilistic forecasting.
result RankNet outperforms baselines significantly, improving MAE by over 10%.
Reinforcement learning controls car speed for safe, efficient, and comfortable driving.
problem Safe, efficient, and comfortable car following during autonomous driving.
method Deep reinforcement learning with a reward function for safety, efficiency, and comfort.
result The model reduces dangerous minimum time to collision to 8% of human drivers and maintains efficient headways.
Bayesian approach improves car-following model calibration and validation.
problem Insufficient data and computational constraints limit accurate model calibration.
method Bayesian machine learning and probabilistic programming.
result Unique parameter sets estimated for each driver, outperforming standard approaches.
Analyzes Twitter users' opinions on self-driving cars.
problem Understanding public perception of self-driving cars.
method Annotated Twitter dataset, topic modeling, sentiment classification using Twitter features.
result People are generally optimistic but also concerned about self-driving cars.
Paper tackles drowsy driving by learning from weakly labeled car acceleration data.
problem Lack of labeled data for estimating driver drowsiness.
method Weakly supervised learning, scalable stochastic optimization.
result Algorithm learns from weakly labeled data, outperforming baseline methods.
Adversarial attacks can fool self-driving cars, changing steering predictions.
problem Security of deep neural networks in self-driving cars.
method Demonstrated adversarial attacks on steering angle prediction model.
result Small image modifications can mislead self-driving car predictions.
Method verifies if observed data fits Lévy-Driven Ornstein-Uhlenbeck process.
problem Verifying if observed data fits Lévy-Driven Ornstein-Uhlenbeck process.
method Estimating parameters and approximating the driving process to test CAR(1) Lévy-driven hypothesis.
result Demonstrates method's effectiveness through simulations and real data examples.
New method identifies drivers from car logs without reverse-engineering CAN protocol.
problem Identifying drivers from in-vehicle network logs without access to exact signal semantics.
method Machine learning techniques applied to off-the-shelf data.
result Driver re-identification accuracy of 75-85% on a dataset of 33 drivers.
GPLVMF improves CARS performance by addressing overfitting and context importance.
problem Overfitting and lack of automatic context importance determination in GP-based CARS.
method GPLVMF applies a non-zero mean function and real-valued latent space to improve GP model performance.
result Significant improvement in performance on real datasets and automatic context importance determination.
Predict steering angles of self-driving cars from images.
problem Predicting steering angles for self-driving cars using image data.
method Used deep learning techniques like Transfer Learning, 3D CNN, LSTM, and ResNet to predict steering angles.
result Both models placed in the top ten of Udacity's challenge.
Pruning filters in CNNs improves interpretability, showing shape-selective filters are crucial for object recognition.
problem Interpreting the complex decision-making process of CNNs is challenging due to their large number of parameters.
method We developed a greedy structural compression scheme that prunes filters based on the classification accuracy reduction (CAR) index.
result Pruned filters in CNNs, especially those in the first and second layers, are more likely to be shape-selective, indicating their importance in object recognition.
Study tackles imbalanced data in car insurance claims prediction.
problem Predicting rare events (claims) in car insurance with imbalanced data.
method Various machine learning techniques (logistic-regression, decision tree, random forest, xgBoost, feed-forward network) applied to imbalanced dataset.
result Comparison of machine learning algorithms' performance in claim occurrence prediction.
Methodology calculates car insurance premiums for partial damage losses.
problem Estimating premiums for partial damage losses in automobile insurance.
method Used generalized linear models to analyze claim frequency and severity.
result Identified key variables influencing claim frequency and severity.
EBM improves car insurance claim severity and frequency prediction while maintaining interpretability.
problem Balancing predictive accuracy and interpretability in insurance claim modeling.
method Combines GAM and cyclic gradient boosting, providing interpretable predictions.
result EBM outperforms benchmark models in claim severity and frequency prediction.
A new model captures car-following and lane-changing behaviors in traffic.
problem Modeling stochastic microscopic traffic behaviors.
method Physics regularized Gaussian process (PRGP) approach.
result The proposed model outperforms previous methods in estimation precision.
This review covers methods for autonomous driving including tracking, prediction, and decision making.
problem Improving autonomous driving through better tracking, prediction, and decision making.
method Approaches based on neural networks, stochastic techniques, and reinforcement learning are discussed.
result Effective methods for autonomous driving are identified and compared.
Deep RL predicts car steering angles from images.
problem Learning steering angles for autonomous cars in simulators.
method Extracts latent representations, trains RL on latent vectors.
result Method learns steering angles without human control signals.
Deep learning and prior maps improve traffic light recognition for autonomous cars.
problem Recognizing traffic lights for autonomous cars in urban environments.
method Combining deep learning-based detection with prior maps for traffic light identification and state recognition.
result The proposed system correctly identified relevant traffic lights along predefined routes.
A novel observer-based method detects and recovers anomalies in CAV sensor readings.
problem Improving safety and security in connected and automated vehicles.
method Combines model-based signal filtering and anomaly detection methods using AEKF and OCSVM.
result The proposed method achieves better anomaly detection performance compared to traditional methods.
Study systemic risk measures and capital allocation rules, showing commonalities.
problem Systemic risk measures and capital allocation in financial systems.
method Developed a general framework to embed axiomatic and injective capital approaches, introduced Aumann-Shapley CAR.
result Aumann-Shapley CAR provides a universal method for capital allocation regardless of risk measurement.
A new pricing model reduces bias in insurance premiums.
problem Insurance pricing fairness and discrimination.
method Adversarial learning and autoencoders for debiasing multiple pricing factors.
result A single pricing model mitigates bias across geographic and car types.
The paper proposes a method to estimate treatment effects using CAR designs with additional covariates.
problem Estimating distributional treatment effects in CAR designs with additional covariates.
method Flexible distribution regression framework that incorporates additional covariates using machine learning methods.
result The proposed estimator attains the semiparametric efficiency bound for distributional treatment effects under CAR.
We approximate the distribution of total expenditure of a retail company over warranty claims incurred in a fixed period [0, T], say the following quarter. We consider two kinds of warranty policies, namely, the non-renewing free replacement warranty policy and the non-renewing pro-rata warranty policy. Our approximati…
PIRL generates interpretable reinforcement learning policies using programming languages.
problem Creating interpretable reinforcement learning policies.
method Neurally Directed Program Search (NDPS) for finding optimal programmatic policies.
result PIRL discovers human-readable, smoother, and transferable policies.
This paper improves context-aware recommender systems by selecting and incorporating relevant low-dimensional contextual information.
problem Generating accurate recommendations is not enough; contextual information can cause issues like battery drain and privacy.
method Developed a feature-selection algorithm based on genetic algorithms to reduce context dimensions while maintaining explainability.
result The approach improves accuracy and transparency in recommendations, outperforming state-of-the-art models.
Statistical models of economic distributions lead to Boltzmann distributions rather than a Pareto power law. This result is supported by two facts: 1. the distributions of income, car sales, marriages or jobs are a matter of chances and luck and not of reason! 2. Data for property, automobile sales, marriages and job m…
Deep RL mimics human driving for collision avoidance in self-driving cars.
problem Developing human-like driving policies for autonomous vehicles in mixed traffic environments.
method Model-free, deep reinforcement learning approach using a combination of rule-based and expert-driven data.
result Demonstrated human-like driving policies through Gaussian process modeling of track position and speed distributions.
Study local sensitivity of HDD and CDD temperature derivatives prices.
problem Understanding how temperature derivatives prices change with small temperature changes.
method Analyzes sensitivity of HDD and CDD futures and options prices to temperature perturbations using a CAR process.
result Identifies the order of the CAR process and its impact on temperature derivatives prices.
Q-learning with nonlinear Q-function can explore effectively without explicit exploration.
problem How to effectively explore in reinforcement learning.
method Q-learning with nonlinear Q-function and no explicit exploration.
result Q-learning with nonlinear Q-function can learn as well as ε-greedy exploration. Deep RL framework teaches cars to drive autonomously.
problem Difficult to apply reinforcement learning to autonomous driving.
method Deep reinforcement learning with Recurrent Neural Networks and attention models.
result Framework successfully learned autonomous maneuvers in complex scenarios.
Deep neural features identify unique vehicles from dash-cam feeds.
problem Identifying unique vehicles in dash-cam feeds for self-driving cars.
method Used pretrained YOLO network feature maps to create deep integrated feature signatures (DIFS) for 700 images of 35 vehicles and 340 images of 17 vehicles.
result Correctly identified unique vehicles at 96.7% for high resolution data and 86.8% for lower resolution data.
Bayesian approach improves car-following model calibration and validation with limited data.
problem Difficulties in calibrating car-following models using limited data for work zones.
method Bayesian programming for data analysis and parameter estimation.
result Bayesian methods enhance model calibration and validation accuracy.