AI in Actuarial Science Ronald Richman
|
|
- Marvin Jordan Wade
- 5 years ago
- Views:
Transcription
1 AI in Actuarial Science Ronald Richman
2 01 AGENDA 1. Introduction 2. Background Machine Learning Deep Learning Five Main Deep Architectures 3. Applications in Actuarial Science 4. Discussion and Conclusion PG 1
3 02 INTRODUCTION This talk is about 3 things: 1. Provide context to understand deep learning 2. Discuss applications of deep learning in actuarial science 3. Provide code to experiment (see last slide) And also PG 2
4 03 THE SHIP IS SAILING PG 3
5 04 WHAT INSPIRED THIS TALK? (1) "The future of insurance will be staffed by bots rather than brokers and AI in favor of actuaries"- Daniel Schreiber, Lemonade Inc. PG 4
6 05 WHAT INSPIRED THIS TALK? (2) We all use Deep Learning Google/Apple/Facebook/Instagram/Pinterest and might use it more in the medium term (self-driving cars) We all help to train Deep Learning Recaptcha But, are actuaries benefiting from Deep Learning? PG 5
7 06 AGENDA 1. Introduction 2. Background Machine Learning Deep Learning Five Main Deep Architectures 3. Applications in Actuarial Science 4. Discussion and Conclusion PG 6
8 07 MACHINE LEARNING Machine Learning is the field concerned with the study of algorithms that allow computer programs to automatically improve through experience (Mitchell 1997) Machine learning approach to AI - systems trained to recognize patterns within data to acquire knowledge (Goodfellow, Bengio and Courville 2016). Different paradigm from earlier attempts to build AI systems: Hard coding knowledge into knowledge bases to solve problems in formal domains defined by mathematical rules. Highly complex tasks e.g. image recognition, scene understanding and inferring semantic concepts (Bengio 2009) more difficult to solve for AI systems. ML Paradigm feed data to the machine and let it figure it out! PG 7
9 08 A MAP OF MACHINE LEARNING Machine Learning Supervised Learning Unsupervised Learning Reinforcement Learning Regression Classification Deep Learning PG 8
10 09 SUPERVISED LEARNING (1) Supervised learning = application of machine learning to datasets that contain features and outputs with the goal of predicting the outputs from the features (Friedman, Hastie and Tibshirani 2009). y (outputs) X (features) More on the French MTPL dataset later. PG 9
11 10 10 SUPERVISED LEARNING (2) y (outputs) X (features) y (outputs) X (features)
12 11 11 UNSUPERVISED LEARNING Unsupervised learning = application of machine learning to datasets containing only features to find structure within these datasets (Sutton and Barto 2018). Task of unsupervised learning is to find meaningful patterns using only the features. Recent example - modelling yield curves using Principal Components Analysis (PCA) for the Interest Rate SCR in SAM Mortality modelling Lee-Carter model uses PCA to reconstruct mortality curves
13 12 12 REINFORCEMENT LEARNING Reinforcement learning = learning action to take in situations in order for an agent to maximise a reward signal (Sutton and Barto 2018).
14 13 13 ML AND ACTUARIAL PROBLEMS Actuarial problems are often supervised regressions implying that: If an actuarial problem can be expressed as a regression, then machine and deep learning techniques can be applied. Short-Term pricing IBNR reserving Mortality modelling Lite valuation models But don t forget about unsupervised learning either!
15 14 14 SO, ML IS JUST REGRESSION, RIGHT? Not exactly. Machine Learning relies on a different approach to building, parameterizing and testing statistical models, based on statistical learning theory. Differences between statistical modelling (i.e. inference), and supervised learning, due to distinction between tasks of predicting and explaining, see Shmueli (2010). Focus on predictive performance leads to: Building algorithms to predict responses instead of specifying a stochastic data generating model (Breiman 2001) favouring models with good predictive performance that are often more difficult to interpret than statistical models. Accepting bias in models if this is expected to reduce the overall prediction error. Quantifying predictive error (i.e. out-of-sample error) by splitting data into training, validation and testing sets, or using by cross-validation.
16 15 15 AGENDA 1. Introduction 2. Background Machine Learning Deep Learning Five Main Deep Architectures 3. Applications in Actuarial Science 4. Discussion and Conclusion
17 16 16 FEATURE ENGINEERING Suppose we realize that Claims depend on Age^2 => enlarge feature space by adding Age^2 to data. Other options add interactions/basis functions e.g. splines y (outputs) X (features) 0.12 rate DrivAge
18 17 17 REPRESENTATION LEARNING In many domains, including actuarial science, traditional approach to designing machine learning systems relies on humans for feature engineering. But: designing features is time consuming/tedious relies on expert knowledge that may not be transferable to a new domain becomes difficult with very high dimensional data Representation (feature) Learning = machine learning approach that allows algorithms automatically to design a set of features that are optimal for a particular task. Traditional examples: Unsupervised = PCA Supervised = PLS Simple/naive RL approaches often fail when applied to high dimensional data
19 18 18 DEEP LEARNING (1) Deep Learning = representation learning technique that automatically constructs hierarchies of complex features composed of simpler representations learned at a shallower level of the model. More popular modern example of deep learning is feed-forward neural networks, which are multi-layered machine learning models, where each layer learns a new representation of the features. The principle: Provide data to the network and let it figure out what and how to learn. Desiderata for AI by Bengio (2009): Ability to learn with little human input the low-level, intermediate, and high-level abstractions that would be useful to represent the kind of complex functions needed for AI tasks.
20 19 19 DEEP LEARNING (2) Major successes achieved using deep learning: Computer vision starting with AlexNet architecture of Krizhevsky, Sutskever and Hinton (2012) and continued with the Inception model of Szegedy, Liu, Jia et al. (2015) Speech recognition (Hannun, Case, Casper et al. 2014). Natural language processing, e.g. Google s neural translation machine (Wu, Schuster, Chen et al. 2016) Winning method in 2018 M4 time series forecasting competition, which used combination of deep neural network with exponentially weighted forecasting model (Makridakis, Spiliotis and Assimakopoulos 2018a). Analysis of GPS data (Brébisson, Simon, Auvolat et al. 2015) Analysis of tabular data (Guo and Berkhahn 2016) (plus other Kaggle competitions)
21 20 20 AGENDA 1. Introduction 2. Background Machine Learning Deep Learning Five Main Deep Architectures 3. Applications in Actuarial Science 4. Discussion and Conclusion
22 21 21 GENTLE INTRODUCTION SINGLE LAYER One layer neural network Circles = variables Lines = connections between inputs and outputs Input layer holds the variables that are input to the network multiplied by weights (coefficients) to get to result Single layer neural network is a GLM!
23 21a 21 aa DEEP FEEDFORWARD NET Deep = multiple layers Feedforward = data travels from left to right Fully connected network = all neurons in layer connected to all neurons in previous layer More complicated representations of input data learned in each hidden layer Example has a vector input and scalar output but can have arbitrary sized inputs and outputs
24 22 22 DEEP AUTOENCODER Deep = multiple layers Autoencoder = network is trained to produce output equal to the input Vector input and output Bottleneck in middle restricts dimension of encoded data in this example, to 1, but can be to multiple dimensions Performs a type of non-linear PCA Encoded data summarizes the input
25 23 23 CONVOLUTIONAL NEURAL NETWORK Data Matrix Filter = *1 0*1 0* *0 0*0 0*0 = = *-1 0*-1 1* Feature Map Convolutional network is locally connected Each neuron (i.e. feature map) in network derived by applying filter to input data Weights of filter learned when fitting network Multiple filters can be applied Useful for data with spatial/temporal structure e.g. images, time series, videos
26 24 24 RECURRENT NEURAL NETWORK O O1 O2 O3 S S1 S2 S3 x x1 x2 x3 Folded Unfolded x = Input vector S = hidden state (layers) O = output Arrows indicate the direction in which data flows. Recurrent network maintains state of hidden neurons over time i.e. network has a memory Several implementations of the recurrent concept which control how network remembers and forgets state Useful for data with temporal structure e.g. natural language and time series
27 25 25 EMBEDDING LAYER Actuary Accountant Quant Statistician Economist Underwriter Actuary Accountant Quant Statistician Economist Underwriter Finance Math Stastistics Liabilities Actuary Accountant Quant Statistician Economist Underwriter Simple way of allowing for categorical data is one-hot encoding = sparse and high dimensional inputs Downside = each vector orthogonal to each other => similar observations not categorized into groups Actuarial solution credibility Embedding layer learns dense vector transformation of sparse input vectors and clusters similar categories together
28 26 26 SUMMARY OF ARCHITECTURES Key principle - Use architecture that expresses useful priors about the data => major performance gains Deep feedforward network structured (tabular) data Deep autoencoder unsupervised learning Convolutional neural network data with spatial/temporal dimension e.g. images and time series Recurrent neural network data with temporal structure Embedding layers categorical data (or real values structured as categorical data)
29 27 27 AGENDA 1. Introduction 2. Background Machine Learning Deep Learning Five Main Deep Architectures 3. Applications in Actuarial Science 4. Discussion and Conclusion
30 28 28 APPLICATIONS IN ACTUARIAL SCIENCE Searches within actuarial literature confined to articles written after 2006, when current resurgence of interest in neural networks began (Goodfellow, Bengio and Courville 2016). Most papers on SSRN/Arxiv = cutting edge? (X = discussed here, else in paper) Pricing of non-life insurance (Noll, Salzmann and Wüthrich 2018; Wüthrich and Buser 2018) X IBNR Reserving (Kuo 2018b; Wüthrich 2018b; Zarkadoulas 2017) X Analysis of telematics data (Gao, Meng and Wüthrich 2018; Gao and Wüthrich 2017; Wüthrich and Buser 2018; Wüthrich 2017) X Mortality forecasting (Hainaut 2018a) Approximating nested stochastic simulations (Hejazi and Jackson 2016, 2017) Forecasting financial markets (Smith, Beyers and De Villiers 2016)
31 29 29 NON-LIFE PRICING (1) Non-life Pricing (tabular data fit with GLMs) seems like obvious application of ML/DL Noll, Salzmann and Wüthrich (2018) is tutorial paper (with code) in which apply GLMs, regression trees, boosting and (shallow) neural networks to French Third Party Liability (TPL) dataset (see slide 17) to model frequency ML approaches outperform GLM Boosted tree performs about as well as neural network.mainly because ML approaches capture some interactions automatically In own analysis, found that surprisingly, off the shelf approaches do not perform particularly well on frequency models. Low signal to noise relationship to blame? (Wüthrich and Buser 2018) These include XGBoost and vanilla deep networks
32 30 30 NON-LIFE PRICING (2) Model OutOfSample GLM GLM_Keras variable dim1 dim2 Deep neural network applied to raw data (i.e. no feature engineering) did not perform well Embedding layers provide NN_shallow NN_no_FE value 0 significant gain in performance over GLM and other NN architectures NN_embed GLM_embed NN_learned_embed Drivage Layers learn a (multidimensional) schedule of rates at each age (shown after applying t-sne) Transfer learning can boost performance of GLM
33 31 31 NON-LIFE PRICING (3) Learned Exposure as.factor(claimnb) Exposure Assumption of frequency GLM rate multiplied by exposure May be inaccurate due to fraud/cancel policy after poor claims performance Best performance from Learned Exposure = allow network to modify exposure measure Figure shows that at lowest level of exposures, network has increased level of exposure As well as for multi-claimants
34 32 32 IBNR RESERVING IBNR Reserving boils down to regression of future reported claim amounts on past => good potential for ML/DL approaches Granular reserving for claim type/property damaged/region/age etc difficult with normal chainladder approach as too much data to derive LDFs judgementally (hopefully would not be done mechanically unless lots of simple and clean data) Wüthrich (2018b) (who provides code + data) extends chain-ladder as a regression model to incorporate features into derivation of LDF C ˆ i, j 1 f ( X ). Ci, j Method produces accurate aggregate and granular reserves DeepTriangle of Kuo (2018b) is less traditional approach. Joint prediction of Paid + Outstanding claims using Recurrent Neural Networks and Embedding Layers Better performance than CL/GLM/Bayesian techniques on Schedule P data from USA
35 33 33 TELEMATICS DATA (1) Telematics produces high dimensional data (position, velocity, acceleration, road type, time of day) at high frequencies not immediately obvious how to incorporate into pricing Sophisticated approaches to analysing telematics data from outside actuarial literature using recurrent neural networks plus embedding layers such as Dong, Li, Yao et al. (2016), Dong, Yuan, Yang et al. (2017) and Wijnands, Thompson, Aschwanden et al. (2018) Within actuarial literature, series of papers by Wüthrich (2017), Gao and Wüthrich (2017) and Gao, Meng and Wüthrich (2018) discuss analysis of velocity and acceleration information from telematics data feed Focus on v-a heatmaps which capture velocity and acceleration profile of driver but these are also high dimensional
36 34 34 TELEMATICS DATA (2) v-a heatmap of driver 20 Heatmap generated using 2 code in Wüthrich (2018c) Shows density i.e. probability that driver is found at location in heatmap acceleration in m/s^ Wüthrich (2017) and Gao and Wüthrich (2017) apply unsupervised learning methods to summarize v-a heat-maps: K-means, PCA and shallow auto-encoders speed in km/h Stunning result = continuous features are highly predictive
37 35 35 TELEMATICS DATA (3) a v Density Why? Goodfellow, Bengio and Courville (2016) : basic idea is features useful for the unsupervised task also be useful for the supervised learning task Analysis using deep convolutional autoencoder with 2 dimensions. Within these dimensions (left hand plot): Right to left = amount of density in high speed bucket Lower to higher = discreteness of the density
38 36 36 AGENDA 1. Introduction 2. Background Machine Learning Deep Learning Five Main Deep Architectures 3. Applications in Actuarial Science 4. Discussion and Conclusion
39 37 37 DISCUSSION Conclusions to be drawn from the examples: Emphasis on predictive performance and potential gains of moving from traditional actuarial and statistical methods to machine and deep learning approaches. Measurement framework utilized within machine learning focus on testing predictive performance. In wider deep learning context, focus on measurable improvements in predictive performance led to refinements and enhancements of deep learning architectures Learned representations from deep neural networks often have readily interpretable meaning Relies on data being available = role for CSI? Combination of deep learning plus traditional methods, refer to M4 Competition
40 38 38 OUTLOOK (1) Deep learning can enhance the predictive power of models built by actuaries, and provide the means potentially to extend actuarial modelling to new types of data Application of deep learning techniques to actuarial problems seems to be rapidly emerging field within actuarial science => appears reasonable to predict more advances in the near-term. Deep learning is not a panacea for all modelling issues - applied to the wrong domain, deep learning will not produce better or more useful results than other techniques. High-frequency and high-dimensional data perhaps most foreign to actuaries trained in analysing structured data and it could be expected that these types of data will become more common and applicable in a number of lines of insurance. Winter might be coming if actuaries do not take the lead in applying deep learning, someone else will.
41 39 39 OUTLOOK (2) Role of guidance and professionalism Element of expert judgement involved in designing and fitting deep neural networks = opportunity for actuaries to become experts in application of AI within Actuarial Science. As with any technique, whether traditional or based on machine learning, actuaries should apply their professional judgement to consider if the results derived from deep neural networks are fit for purpose and in the public interest. Recent discussions online of ethics of deep learning models and potential of hidden bias Opportunity for actuarial societies to lead with guidance for members on applying AI within Actuarial Science
42 40 40 CONCLUSION Thank you for your attention. Any Questions? Contact: Code: Blog:
43 41 41 REFERENCES Bengio, Y "Learning deep architectures for AI", Foundations and trends in Machine Learning 2(1): Breiman, L "Statistical modeling: The two cultures (with comments and a rejoinder by the author)", Statistical Science 16(3): De Brébisson, A., É. Simon, A. Auvolat, P. Vincent et al "Artificial neural networks applied to taxi destination prediction", arxiv arxiv: Friedman, J., T. Hastie and R. Tibshirani The Elements of Statistical Learning : Data Mining, Inference, and Prediction. New York: Springer-Verlag. Gabrielli, A. and M. Wüthrich "An Individual Claims History Simulation Machine", Risks 6(2):29. Gao, G., S. Meng and M. Wüthrich Claims Frequency Modeling Using Telematics Car Driving Data. SSRN. Accessed: 29 June Gao, G. and M. Wüthrich Feature Extraction from Telematics Car Driving Heatmaps. SSRN. Accessed: June Goodfellow, I., Y. Bengio and A. Courville Deep Learning. MIT Press. Guo, C. and F. Berkhahn "Entity embeddings of categorical variables", arxiv arxiv: Hainaut, D "A neural-network analyzer for mortality forecast", Astin Bulletin 48(2): Hannun, A., C. Case, J. Casper, B. Catanzaro et al "Deep speech: Scaling up end-to-end speech recognition", arxiv arxiv: Hejazi, S. and K. Jackson "A neural network approach to efficient valuation of large portfolios of variable annuities", Insurance: Mathematics and Economics 70: Krizhevsky, A., I. Sutskever and G. Hinton "Imagenet classification with deep convolutional neural networks," Paper presented at Advances in Neural Information Processing Systems Kuo, K "DeepTriangle: A Deep Learning Approach to Loss Reserving", arxiv arxiv: Makridakis, S., E. Spiliotis and V. Assimakopoulos "The M4 Competition: Results, findings, conclusion and way forward", International Journal of Forecasting Mitchell, T Machine learning. McGraw-Hill Boston, MA. Noll, A., R. Salzmann and M. Wüthrich Case Study: French Motor Third-Party Liability Claims. SSRN. Accessed: 17 June Schreiber, D The Future of Insurance. DIA Munich 2017: Accessed: 17 June Shmueli, G "To explain or to predict?", Statistical Science: Smith, M., F. Beyers and J. De Villiers "A method of parameterising a feed forward multi-layered perceptron artificial neural network, with reference to South African financial markets", South African Actuarial Journal 16(1): Sutton, R. and A. Barto Reinforcement learning: An introduction, Second Edition. MIT Press. Szegedy, C., W. Liu, Y. Jia, P. Sermanet et al. "Going deeper with convolutions," Paper presented at. Wu, Y., M. Schuster, Z. Chen, Q. Le et al "Google's neural machine translation system: Bridging the gap between human and machine translation", arxiv arxiv: Wüthrich, M. 2018a. Neural networks applied to chain-ladder reserving. SSRN. Accessed: 1 July Wüthrich, M. 2018b. v-a Heatmap Simulation Machine. Accessed: 1 July Wüthrich, M. and C. Buser Data analytics for non-life insurance pricing. Swiss Finance Institute Research Paper. Accessed: 17 June Wüthrich, M.V "Covariate selection from telematics car driving data", European Actuarial Journal 7(1):
AI in Actuarial Science
AI in Actuarial Science By Ronald Richman Presented at the Actuarial Society of South Africa s 2018 Convention 24 25 October 2018, Cape Town International Convention Centre ABSTRACT Rapid advances in Artificial
More informationMachine Learning and the Insurance Industry Prof. John D. Kelleher
Machine Learning and the Insurance Industry Prof. John D. Kelleher ADAPT Centre, Dublin Institute of Technology john.d.kelleher@dit.ie The ADAPT Centre is funded under the SFI Research Centres Programme
More informationSTOCK PRICE PREDICTION: KOHONEN VERSUS BACKPROPAGATION
STOCK PRICE PREDICTION: KOHONEN VERSUS BACKPROPAGATION Alexey Zorin Technical University of Riga Decision Support Systems Group 1 Kalkyu Street, Riga LV-1658, phone: 371-7089530, LATVIA E-mail: alex@rulv
More informationIran s Stock Market Prediction By Neural Networks and GA
Iran s Stock Market Prediction By Neural Networks and GA Mahmood Khatibi MS. in Control Engineering mahmood.khatibi@gmail.com Habib Rajabi Mashhadi Associate Professor h_mashhadi@ferdowsi.um.ac.ir Electrical
More informationInternational Journal of Computer Engineering and Applications, Volume XII, Issue II, Feb. 18, ISSN
Volume XII, Issue II, Feb. 18, www.ijcea.com ISSN 31-3469 AN INVESTIGATION OF FINANCIAL TIME SERIES PREDICTION USING BACK PROPAGATION NEURAL NETWORKS K. Jayanthi, Dr. K. Suresh 1 Department of Computer
More informationPredictive modelling around the world Peter Banthorpe, RGA Kevin Manning, Milliman
Predictive modelling around the world Peter Banthorpe, RGA Kevin Manning, Milliman 11 November 2013 Agenda Introduction to predictive analytics Applications overview Case studies Conclusions and Q&A Introduction
More informationInternational Journal of Computer Engineering and Applications, Volume XII, Issue II, Feb. 18, ISSN
International Journal of Computer Engineering and Applications, Volume XII, Issue II, Feb. 18, www.ijcea.com ISSN 31-3469 AN INVESTIGATION OF FINANCIAL TIME SERIES PREDICTION USING BACK PROPAGATION NEURAL
More informationUPDATED IAA EDUCATION SYLLABUS
II. UPDATED IAA EDUCATION SYLLABUS A. Supporting Learning Areas 1. STATISTICS Aim: To enable students to apply core statistical techniques to actuarial applications in insurance, pensions and emerging
More informationHow Can YOU Use it? Artificial Intelligence for Actuaries. SOA Annual Meeting, Gaurav Gupta. Session 058PD
Artificial Intelligence for Actuaries How Can YOU Use it? SOA Annual Meeting, 2018 Session 058PD Gaurav Gupta Founder & CEO ggupta@quaerainsights.com Audience Poll What is my level of AI understanding?
More informationMachine Learning in mathematical Finance
Machine Learning in mathematical Finance Josef Teichmann ETH Zürich December 15, 2017 Josef Teichmann (ETH Zürich) Machine Learning in mathematical Finance December 15, 2017 1 / 37 1 Introduction 2 Machine
More informationPredicting Economic Recession using Data Mining Techniques
Predicting Economic Recession using Data Mining Techniques Authors Naveed Ahmed Kartheek Atluri Tapan Patwardhan Meghana Viswanath Predicting Economic Recession using Data Mining Techniques Page 1 Abstract
More informationLeverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks
Leverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks Yangtuo Peng A THESIS SUBMITTED TO THE FACULTY OF GRADUATE STUDIES IN PARTIAL FULFILLMENT OF THE
More informationA Novel Prediction Method for Stock Index Applying Grey Theory and Neural Networks
The 7th International Symposium on Operations Research and Its Applications (ISORA 08) Lijiang, China, October 31 Novemver 3, 2008 Copyright 2008 ORSC & APORC, pp. 104 111 A Novel Prediction Method for
More informationdistribution of the best bid and ask prices upon the change in either of them. Architecture Each neural network has 4 layers. The standard neural netw
A Survey of Deep Learning Techniques Applied to Trading Published on July 31, 2016 by Greg Harris http://gregharris.info/a-survey-of-deep-learning-techniques-applied-t o-trading/ Deep learning has been
More informationAre New Modeling Techniques Worth It?
Are New Modeling Techniques Worth It? Tom Zougas PhD PEng, Manager Data Science, TransUnion TORONTO SAS USER GROUP MAY 2, 2018 Are New Modeling Techniques Worth It? Presenter Tom Zougas PhD PEng, Manager
More informationDeep Learning for Forecasting Stock Returns in the Cross-Section
Deep Learning for Forecasting Stock Returns in the Cross-Section Masaya Abe 1 and Hideki Nakayama 2 1 Nomura Asset Management Co., Ltd., Tokyo, Japan m-abe@nomura-am.co.jp 2 The University of Tokyo, Tokyo,
More informationLectures and Seminars in Insurance Mathematics and Related Fields at ETH Zurich. Spring Semester 2019
December 2018 Lectures and Seminars in Insurance Mathematics and Related Fields at ETH Zurich Spring Semester 2019 Quantitative Risk Management, by Prof. Dr. Patrick Cheridito, #401-3629-00L This course
More informationExpanding Predictive Analytics Through the Use of Machine Learning
Expanding Predictive Analytics Through the Use of Machine Learning Thursday, February 28, 2013, 11:10 a.m. Chris Cooksey, FCAS, MAAA Chief Actuary EagleEye Analytics Columbia, S.C. Christopher Cooksey,
More informationStock Trading Following Stock Price Index Movement Classification Using Machine Learning Techniques
Stock Trading Following Stock Price Index Movement Classification Using Machine Learning Techniques 6.1 Introduction Trading in stock market is one of the most popular channels of financial investments.
More informationMaking the Link between Actuaries and Data Science
Making the Link between Actuaries and Data Science Simon Lee, Cecilia Chow, Thibault Imbert AXA Asia 2 nd ASHK General Insurance & Data Analytics Seminar Friday 7 October 2016 1 Agenda Data Driving Insurers
More informationSTOCK MARKET PREDICTION AND ANALYSIS USING MACHINE LEARNING
STOCK MARKET PREDICTION AND ANALYSIS USING MACHINE LEARNING Sumedh Kapse 1, Rajan Kelaskar 2, Manojkumar Sahu 3, Rahul Kamble 4 1 Student, PVPPCOE, Computer engineering, PVPPCOE, Maharashtra, India 2 Student,
More informationApplication of Deep Learning to Algorithmic Trading
Application of Deep Learning to Algorithmic Trading Guanting Chen [guanting] 1, Yatong Chen [yatong] 2, and Takahiro Fushimi [tfushimi] 3 1 Institute of Computational and Mathematical Engineering, Stanford
More informationThe Use of Artificial Neural Network for Forecasting of FTSE Bursa Malaysia KLCI Stock Price Index
The Use of Artificial Neural Network for Forecasting of FTSE Bursa Malaysia KLCI Stock Price Index Soleh Ardiansyah 1, Mazlina Abdul Majid 2, JasniMohamad Zain 2 Faculty of Computer System and Software
More informationLazy Prices: Vector Representations of Financial Disclosures and Market Outperformance
Lazy Prices: Vector Representations of Financial Disclosures and Market Outperformance Kuspa Kai kuspakai@stanford.edu Victor Cheung hoche@stanford.edu Alex Lin alin719@stanford.edu Abstract The Efficient
More informationSession 5. Predictive Modeling in Life Insurance
SOA Predictive Analytics Seminar Hong Kong 29 Aug. 2018 Hong Kong Session 5 Predictive Modeling in Life Insurance Jingyi Zhang, Ph.D Predictive Modeling in Life Insurance JINGYI ZHANG PhD Scientist Global
More informationExtreme Market Prediction for Trading Signal with Deep Recurrent Neural Network
Extreme Market Prediction for Trading Signal with Deep Recurrent Neural Network Zhichen Lu 1,2,3, Wen Long 1,2,3, and Ying Guo 1,2,3 School of Economics & Management, University of Chinese Academy of Sciences,
More informationHEALTH ACTUARIES AND BIG DATA
HEALTH ACTUARIES AND BIG DATA What is Big Data? The term Big Data does not only refer to very large datasets. It is typically understood to refer to high volumes of data, requiring high velocity of ingestion
More informationCOMPARING NEURAL NETWORK AND REGRESSION MODELS IN ASSET PRICING MODEL WITH HETEROGENEOUS BELIEFS
Akademie ved Leske republiky Ustav teorie informace a automatizace Academy of Sciences of the Czech Republic Institute of Information Theory and Automation RESEARCH REPORT JIRI KRTEK COMPARING NEURAL NETWORK
More informationUNDERSTANDING ML/DL MODELS USING INTERACTIVE VISUALIZATION TECHNIQUES
UNDERSTANDING ML/DL MODELS USING INTERACTIVE VISUALIZATION TECHNIQUES Chakri Cherukuri Senior Researcher Quantitative Financial Research Group 1 OUTLINE Introduction Applied machine learning in finance
More informationApplications of Neural Networks
Applications of Neural Networks MPhil ACS Advanced Topics in NLP Laura Rimell 25 February 2016 1 NLP Neural Network Applications Language Models Word Embeddings Tagging Parsing Sentiment Machine Translation
More informationWho s Afraid of Artificial Intelligence? Frank Cuypers
Who s Afraid of Artificial Intelligence? Frank Cuypers Scenario 2016 2020 2025 2030 2035 Solvency II initiates New players flood the market with digital alternatives to insurance Insurance industry flood
More informationApplication of Data Mining Technology in the Loss of Customers in Automobile Insurance Enterprises
International Journal of Data Science and Analysis 2018; 4(1): 1-5 http://www.sciencepublishinggroup.com/j/ijdsa doi: 10.11648/j.ijdsa.20180401.11 ISSN: 2575-1883 (Print); ISSN: 2575-1891 (Online) Application
More informationSubmissions must confirm the following additional requirements:
Best Paper Awards As part of the International Congress of Actuaries in 2018, the Scientific Committee will award a number of Best Paper Awards in six given subject areas. After consideration of all submissions,
More informationAn introduction to Machine learning methods and forecasting of time series in financial markets
An introduction to Machine learning methods and forecasting of time series in financial markets Mark Wong markwong@kth.se December 10, 2016 Abstract The goal of this paper is to give the reader an introduction
More informationInternational Journal of Research in Engineering Technology - Volume 2 Issue 5, July - August 2017
RESEARCH ARTICLE OPEN ACCESS The technical indicator Z-core as a forecasting input for neural networks in the Dutch stock market Gerardo Alfonso Department of automation and systems engineering, University
More informationStock market price index return forecasting using ANN. Gunter Senyurt, Abdulhamit Subasi
Stock market price index return forecasting using ANN Gunter Senyurt, Abdulhamit Subasi E-mail : gsenyurt@ibu.edu.ba, asubasi@ibu.edu.ba Abstract Even though many new data mining techniques have been introduced
More informationInternational Journal of Computer Science Trends and Technology (IJCST) Volume 5 Issue 2, Mar Apr 2017
RESEARCH ARTICLE Stock Selection using Principal Component Analysis with Differential Evolution Dr. Balamurugan.A [1], Arul Selvi. S [2], Syedhussian.A [3], Nithin.A [4] [3] & [4] Professor [1], Assistant
More informationarxiv: v1 [cs.ce] 11 Sep 2018
Visual Attention Model for Cross-sectional Stock Return Prediction and End-to-End Multimodal Market Representation Learning Ran Zhao Carnegie Mellon University rzhao1@cs.cmu.edu Arun Verma Bloomberg averma3@bloomberg.net
More informationTwo kinds of neural networks, a feed forward multi layer Perceptron (MLP)[1,3] and an Elman recurrent network[5], are used to predict a company's
LITERATURE REVIEW 2. LITERATURE REVIEW Detecting trends of stock data is a decision support process. Although the Random Walk Theory claims that price changes are serially independent, traders and certain
More informationApplication of Innovations Feedback Neural Networks in the Prediction of Ups and Downs Value of Stock Market *
Proceedings of the 6th World Congress on Intelligent Control and Automation, June - 3, 006, Dalian, China Application of Innovations Feedback Neural Networks in the Prediction of Ups and Downs Value of
More informationBeyond GLMs. Xavier Conort & Colin Priest
Beyond GLMs Xavier Conort & Colin Priest 1 Agenda 1. GLMs and Actuaries 2. Extensions to GLMs 3. Automating GLM model building 4. Best practice predictive modelling 5. Conclusion 2 1) GLMs Linear models
More informationRisk Element Transmission Model of Construction Project Chain Based on System Dynamic
Research Journal of Applied Sciences, Engineering and Technology 5(4): 14071412, 2013 ISSN: 20407459; eissn: 20407467 Maxwell Scientific Organization, 2013 Submitted: July 09, 2012 Accepted: August 08,
More informationMachine Learning for Physicists Lecture 10. Summer 2017 University of Erlangen-Nuremberg Florian Marquardt
Machine Learning for Physicists Lecture 10 Summer 2017 University of Erlangen-Nuremberg Florian Marquardt Function/Image representation Image classification [Handwriting recognition] Convolutional nets
More informationApplications of Neural Networks in Stock Market Prediction
Applications of Neural Networks in Stock Market Prediction -An Approach Based Analysis Shiv Kumar Goel 1, Bindu Poovathingal 2, Neha Kumari 3 1Asst. Professor, Vivekanand Education Society Institute of
More informationA Comparative Study of Ensemble-based Forecasting Models for Stock Index Prediction
Association for Information Systems AIS Electronic Library (AISeL) MWAIS 206 Proceedings Midwest (MWAIS) Spring 5-9-206 A Comparative Study of Ensemble-based Forecasting Models for Stock Index Prediction
More informationAbstract Making good predictions for stock prices is an important task for the financial industry. The way these predictions are carried out is often
Abstract Making good predictions for stock prices is an important task for the financial industry. The way these predictions are carried out is often by using artificial intelligence that can learn from
More informationBarapatre Omprakash et.al; International Journal of Advance Research, Ideas and Innovations in Technology
ISSN: 2454-132X Impact factor: 4.295 (Volume 4, Issue 2) Available online at: www.ijariit.com Stock Price Prediction using Artificial Neural Network Omprakash Barapatre omprakashbarapatre@bitraipur.ac.in
More information2017 IAA EDUCATION SYLLABUS
2017 IAA EDUCATION SYLLABUS 1. STATISTICS Aim: To enable students to apply core statistical techniques to actuarial applications in insurance, pensions and emerging areas of actuarial practice. 1.1 RANDOM
More informationCS 461: Machine Learning Lecture 8
CS 461: Machine Learning Lecture 8 Dr. Kiri Wagstaff kiri.wagstaff@calstatela.edu 2/23/08 CS 461, Winter 2008 1 Plan for Today Review Clustering Reinforcement Learning How different from supervised, unsupervised?
More informationMachine Learning in Risk Forecasting and its Application in Low Volatility Strategies
NEW THINKING Machine Learning in Risk Forecasting and its Application in Strategies By Yuriy Bodjov Artificial intelligence and machine learning are two terms that have gained increased popularity within
More informationRecurrent Residual Network
Recurrent Residual Network 2016/09/23 Abstract This work briefly introduces the recurrent residual network which is a combination of the residual network and the long short term memory network(lstm). The
More informationNovel Approaches to Sentiment Analysis for Stock Prediction
Novel Approaches to Sentiment Analysis for Stock Prediction Chris Wang, Yilun Xu, Qingyang Wang Stanford University chrwang, ylxu, iriswang @ stanford.edu Abstract Stock market predictions lend themselves
More information$tock Forecasting using Machine Learning
$tock Forecasting using Machine Learning Greg Colvin, Garrett Hemann, and Simon Kalouche Abstract We present an implementation of 3 different machine learning algorithms gradient descent, support vector
More informationPredictive Modelling. Document Turning Big Data into Big Opportunities
Predictive Modelling Document 218081 Turning Big Data into Big Opportunities Essays on Predictive Modelling: Turning Big Data into Big Opportunities In recent years, data has become a key driver of economic
More informationBased on BP Neural Network Stock Prediction
Based on BP Neural Network Stock Prediction Xiangwei Liu Foundation Department, PLA University of Foreign Languages Luoyang 471003, China Tel:86-158-2490-9625 E-mail: liuxwletter@163.com Xin Ma Foundation
More informationIntroducing GEMS a Novel Technique for Ensemble Creation
Introducing GEMS a Novel Technique for Ensemble Creation Ulf Johansson 1, Tuve Löfström 1, Rikard König 1, Lars Niklasson 2 1 School of Business and Informatics, University of Borås, Sweden 2 School of
More informationHKUST CSE FYP , TEAM RO4 OPTIMAL INVESTMENT STRATEGY USING SCALABLE MACHINE LEARNING AND DATA ANALYTICS FOR SMALL-CAP STOCKS
HKUST CSE FYP 2017-18, TEAM RO4 OPTIMAL INVESTMENT STRATEGY USING SCALABLE MACHINE LEARNING AND DATA ANALYTICS FOR SMALL-CAP STOCKS MOTIVATION MACHINE LEARNING AND FINANCE MOTIVATION SMALL-CAP MID-CAP
More informationSYLLABUS OF BASIC EDUCATION FALL 2017 Advanced Ratemaking Exam 8
The syllabus for this four-hour exam is defined in the form of learning objectives, knowledge statements, and readings. set forth, usually in broad terms, what the candidate should be able to do in actual
More informationReserving Risk and Solvency II
Reserving Risk and Solvency II Peter England, PhD Partner, EMB Consultancy LLP Applied Probability & Financial Mathematics Seminar King s College London November 21 21 EMB. All rights reserved. Slide 1
More informationBusiness Strategies in Credit Rating and the Control of Misclassification Costs in Neural Network Predictions
Association for Information Systems AIS Electronic Library (AISeL) AMCIS 2001 Proceedings Americas Conference on Information Systems (AMCIS) December 2001 Business Strategies in Credit Rating and the Control
More informationStock Market Trend Prediction Using Recurrent Convolutional Neural Networks
Stock Market Trend Prediction Using Recurrent Convolutional Neural Networks Bo Xu, Dongyu Zhang, Shaowu Zhang, Hengchao Li, and Hongfei Lin (&) School of Computer Science and Technology, Dalian University
More informationLecture 3: Factor models in modern portfolio choice
Lecture 3: Factor models in modern portfolio choice Prof. Massimo Guidolin Portfolio Management Spring 2016 Overview The inputs of portfolio problems Using the single index model Multi-index models Portfolio
More informationApplication of Big Data Analytics via Soft Computing. Yunus Yetis
Application of Big Data Analytics via Soft Computing Yunus Yetis INTRODUCTION Ø System of Systems (SoS) and cyberphysic are integrated, independently operating systems working in a cooperative mode to
More informationForeign Exchange Forecasting via Machine Learning
Foreign Exchange Forecasting via Machine Learning Christian González Rojas cgrojas@stanford.edu Molly Herman mrherman@stanford.edu I. INTRODUCTION The finance industry has been revolutionized by the increased
More informationAn enhanced artificial neural network for stock price predications
An enhanced artificial neural network for stock price predications Jiaxin MA Silin HUANG School of Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR S. H. KWOK HKUST Business
More informationExploring the Potential of Image-based Deep Learning in Insurance. Luisa F. Polanía Cabrera
Exploring the Potential of Image-based Deep Learning in Insurance Luisa F. Polanía Cabrera 1 Madison, Wisconsin based American Family Insurance is the nation's third-largest mutual property/casualty insurance
More informationImproving Stock Price Prediction with SVM by Simple Transformation: The Sample of Stock Exchange of Thailand (SET)
Thai Journal of Mathematics Volume 14 (2016) Number 3 : 553 563 http://thaijmath.in.cmu.ac.th ISSN 1686-0209 Improving Stock Price Prediction with SVM by Simple Transformation: The Sample of Stock Exchange
More informationHow Advanced Pricing Analysis Can Support Underwriting by Claudine Modlin, FCAS, MAAA
How Advanced Pricing Analysis Can Support Underwriting by Claudine Modlin, FCAS, MAAA September 21, 2014 2014 Towers Watson. All rights reserved. 3 What Is Predictive Modeling Predictive modeling uses
More informationSubject CS2A Risk Modelling and Survival Analysis Core Principles
` Subject CS2A Risk Modelling and Survival Analysis Core Principles Syllabus for the 2019 exams 1 June 2018 Copyright in this Core Reading is the property of the Institute and Faculty of Actuaries who
More informationPredictive Risk Categorization of Retail Bank Loans Using Data Mining Techniques
National Conference on Recent Advances in Computer Science and IT (NCRACIT) International Journal of Scientific Research in Computer Science, Engineering and Information Technology 2018 IJSRCSEIT Volume
More informationBond Market Prediction using an Ensemble of Neural Networks
Bond Market Prediction using an Ensemble of Neural Networks Bhagya Parekh Naineel Shah Rushabh Mehta Harshil Shah ABSTRACT The characteristics of a successful financial forecasting system are the exploitation
More informationSession 3. Life/Health Insurance technical session
SOA Big Data Seminar 13 Nov. 2018 Jakarta, Indonesia Session 3 Life/Health Insurance technical session Anilraj Pazhety Life Health Technical Session ANILRAJ PAZHETY MS (BUSINESS ANALYTICS), MBA, BE (CS)
More informationFeedforward Neural Networks for Sentiment Detection in Financial News
World Journal of Social Sciences Vol. 2. No. 4. July 2012. Pp. 218 234 Feedforward Neural Networks for Sentiment Detection in Financial News Caslav Bozic* and Detlef Seese* With a rise of algorithmic trading
More informationAccepted Manuscript AIRMS: A RISK MANAGEMENT TOOL USING MACHINE LEARNING. Spyros K. Chandrinos, Georgios Sakkas, Nikos D. Lagaros
Accepted Manuscript AIRMS: A RISK MANAGEMENT TOOL USING MACHINE LEARNING Spyros K. Chandrinos, Georgios Sakkas, Nikos D. Lagaros PII: DOI: Reference: S0957-4174(18)30190-8 10.1016/j.eswa.2018.03.044 ESWA
More informationPredictive Model Learning of Stochastic Simulations. John Hegstrom, FSA, MAAA
Predictive Model Learning of Stochastic Simulations John Hegstrom, FSA, MAAA Table of Contents Executive Summary... 3 Choice of Predictive Modeling Techniques... 4 Neural Network Basics... 4 Financial
More informationAdvanced analytics and the future: Insurers boldly explore new frontiers. 2017/2018 P&C Insurance Advanced Analytics Survey Results Summary (Canada)
Advanced analytics and the future: Insurers boldly explore new frontiers 2017/2018 P&C Insurance Advanced Analytics Survey Results Summary (Canada) Introduction: Insurers boldly explore new analytics frontiers
More informationPrediction of Stock Closing Price by Hybrid Deep Neural Network
Available online www.ejaet.com European Journal of Advances in Engineering and Technology, 2018, 5(4): 282-287 Research Article ISSN: 2394-658X Prediction of Stock Closing Price by Hybrid Deep Neural Network
More informationImportance Sampling for Fair Policy Selection
Importance Sampling for Fair Policy Selection Shayan Doroudi Carnegie Mellon University Pittsburgh, PA 15213 shayand@cs.cmu.edu Philip S. Thomas Carnegie Mellon University Pittsburgh, PA 15213 philipt@cs.cmu.edu
More informationReserve Risk Modelling: Theoretical and Practical Aspects
Reserve Risk Modelling: Theoretical and Practical Aspects Peter England PhD ERM and Financial Modelling Seminar EMB and The Israeli Association of Actuaries Tel-Aviv Stock Exchange, December 2009 2008-2009
More informationForecasting stock market prices
ICT Innovations 2010 Web Proceedings ISSN 1857-7288 107 Forecasting stock market prices Miroslav Janeski, Slobodan Kalajdziski Faculty of Electrical Engineering and Information Technologies, Skopje, Macedonia
More informationWC-5 Just How Credible Is That Employer? Exploring GLMs and Multilevel Modeling for NCCI s Excess Loss Factor Methodology
Antitrust Notice The Casualty Actuarial Society is committed to adhering strictly to the letter and spirit of the antitrust laws. Seminars conducted under the auspices of the CAS are designed solely to
More informationAnalysis on the Input-Output Relevancy between China s Financial Industry and Three Major Industries
International Journal of Economics and Finance; Vol. 8, No. 7; 2016 ISSN 1916-971X E-ISSN 1916-9728 Published by Canadian Center of Science and Education Analysis on the Input-Output Relevancy between
More informationInsurance Actuarial Analysis. Max Europe Holdings Ltd Dublin
Paradigm Shifts in General Insurance Actuarial Analysis Manalur Sandilya Max Europe Holdings Ltd Dublin FOCUS FROM CLASS ANALYSIS TO INDIVIDUAL ANALYSIS EVOLUTIONARY PACE EXTERNAL DRIVERS AVAILABILITY
More informationKeywords: artificial neural network, backpropagtion algorithm, derived parameter.
Volume 5, Issue 2, February 2015 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Stock Price
More informationA Novel Method of Trend Lines Generation Using Hough Transform Method
International Journal of Computing Academic Research (IJCAR) ISSN 2305-9184, Volume 6, Number 4 (August 2017), pp.125-135 MEACSE Publications http://www.meacse.org/ijcar A Novel Method of Trend Lines Generation
More informationECONOMIC CAPITAL MODELING CARe Seminar JUNE 2016
ECONOMIC CAPITAL MODELING CARe Seminar JUNE 2016 Boston Catherine Eska The Hanover Insurance Group Paul Silberbush Guy Carpenter & Co. Ronald Wilkins - PartnerRe Economic Capital Modeling Safe Harbor Notice
More informationAccepted Manuscript. Enterprise Credit Risk Evaluation Based on Neural Network Algorithm. Xiaobing Huang, Xiaolian Liu, Yuanqian Ren
Accepted Manuscript Enterprise Credit Risk Evaluation Based on Neural Network Algorithm Xiaobing Huang, Xiaolian Liu, Yuanqian Ren PII: S1389-0417(18)30213-4 DOI: https://doi.org/10.1016/j.cogsys.2018.07.023
More informationBond Pricing AI. Liquidity Risk Management Analytics.
Bond Pricing AI Liquidity Risk Management Analytics www.overbond.com Fixed Income Artificial Intelligence The financial services market is embracing digital processes and artificial intelligence applications
More informationWHITEPAPER
WHITEPAPER 12.27.2017 TABLE OF CONTENT SUMMARY 3 INTRODUCTION 4 1.1. Problem 4 1.2. Solution 5 2. REVIEW OF USED TECHNOLOGIES 6 2.1. Technical Indicators 6 2.2. Machine learning 6 2.3. Artificial neural
More informationAn Improved Approach for Business & Market Intelligence using Artificial Neural Network
Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320 088X IMPACT FACTOR: 5.258 IJCSMC,
More information[D7] PROBABILITY DISTRIBUTION OF OUTSTANDING LIABILITY FROM INDIVIDUAL PAYMENTS DATA Contributed by T S Wright
Faculty and Institute of Actuaries Claims Reserving Manual v.2 (09/1997) Section D7 [D7] PROBABILITY DISTRIBUTION OF OUTSTANDING LIABILITY FROM INDIVIDUAL PAYMENTS DATA Contributed by T S Wright 1. Introduction
More informationCurve fitting for calculating SCR under Solvency II
Curve fitting for calculating SCR under Solvency II Practical insights and best practices from leading European Insurers Leading up to the go live date for Solvency II, insurers in Europe are in search
More informationAcademic Research Review. Algorithmic Trading using Neural Networks
Academic Research Review Algorithmic Trading using Neural Networks EXECUTIVE SUMMARY In this paper, we attempt to use a neural network to predict opening prices of a set of equities which is then fed into
More informationQuantile Regression. By Luyang Fu, Ph. D., FCAS, State Auto Insurance Company Cheng-sheng Peter Wu, FCAS, ASA, MAAA, Deloitte Consulting
Quantile Regression By Luyang Fu, Ph. D., FCAS, State Auto Insurance Company Cheng-sheng Peter Wu, FCAS, ASA, MAAA, Deloitte Consulting Agenda Overview of Predictive Modeling for P&C Applications Quantile
More informationDr. P. O. Asagba Computer Science Department, Faculty of Science, University of Port Harcourt, Port Harcourt, PMB 5323, Choba, Nigeria
PREDICTING THE NIGERIAN STOCK MARKET USING ARTIFICIAL NEURAL NETWORK S. Neenwi Computer Science Department, Rivers State Polytechnic, Bori, PMB 20, Rivers State, Nigeria. Dr. P. O. Asagba Computer Science
More informationA TEMPORAL PATTERN APPROACH FOR PREDICTING WEEKLY FINANCIAL TIME SERIES
A TEMPORAL PATTERN APPROACH FOR PREDICTING WEEKLY FINANCIAL TIME SERIES DAVID H. DIGGS Department of Electrical and Computer Engineering Marquette University P.O. Box 88, Milwaukee, WI 532-88, USA Email:
More informationScaling SGD Batch Size to 32K for ImageNet Training
Scaling SGD Batch Size to 32K for ImageNet Training Yang You Computer Science Division of UC Berkeley youyang@cs.berkeley.edu Yang You (youyang@cs.berkeley.edu) 32K SGD Batch Size CS Division of UC Berkeley
More informationMulti-year non-life insurance risk of dependent lines of business
Lukas J. Hahn University of Ulm & ifa Ulm, Germany EAJ 2016 Lyon, France September 7, 2016 Multi-year non-life insurance risk of dependent lines of business The multivariate additive loss reserving model
More informationPrediction Using Back Propagation and k- Nearest Neighbor (k-nn) Algorithm
Prediction Using Back Propagation and k- Nearest Neighbor (k-nn) Algorithm Tejaswini patil 1, Karishma patil 2, Devyani Sonawane 3, Chandraprakash 4 Student, Dept. of computer, SSBT COET, North Maharashtra
More informationDesign and Application of Artificial Neural Networks for Predicting the Values of Indexes on the Bulgarian Stock Market
Design and Application of Artificial Neural Networks for Predicting the Values of Indexes on the Bulgarian Stock Market Veselin L. Shahpazov Institute of Information and Communication Technologies, Bulgarian
More information