Think of this modest website as an “expanded business card” to help you get to know me better.
I’m Itai Dattner, Founder and CEO at 360° Data Science. I’ve always had an interest in a wide range of disciplines, from business and research to teaching and music. That is why I find data science to be such a perfect fit for me – it is where data, people, technology and endless domains all intersect.
I have a PhD in statistics, I’m an entrepreneur, a data scientist and AI expert with more than 20 years of experience. My professional background includes business management & development, R&D management and a number of academic positions. Below you can find a brief recap of my career.
I have experience consulting a variety of companies, helping them develop business models – starting from characterizing, prioritizing, and selecting business use cases to defining business promises and product requirements, and ultimately merging these with the R&D plan. I have led R&D teams and also supported them as a consultant. This includes writing yearly working plans, creating budgets and setting goals and objectives for R&D units. I am skilled at presenting products and technology to investors and international business partners.
Recently I established a data science center unit for a large Israeli industrial company. I was involved in every aspect of the process, including designing the data science center within the R&D department, recruiting the right professional team, developing and implementing R&D methodologies as well as training and mentoring the staff. I stayed on to manage the data center for a while after it was established.
Ten years ago, I Served as a data manager and biostatistician in the National Institute of Child Health and Human Development (NICHD)’s EAGeR clinical trial. I took a substantial part in building the Data Coordinating Center for this trial from the ground up, including recruiting staff, developing working methodologies, conducting complex statistical analyses, compiling reports, automation of complex routine tasks, responsibility for development of designated web applications for medical staff, and more.
My business experience goes back to the packaging industry. We had a family factory where we manufactured cardboard packaging. I was involved in all aspects of the business, from hands-on manufacturing to inventory management, product pricing and business development, in Israel and abroad. That’s when I began using what we now call “data science” to improve daily business tasks and to create value for the business. For example, I automated many daily processes using Java and other computational tools, which led to better management and decision making.
Besides management, my experience also includes hands-on programming. I have had the opportunity to use a variety of computational tools over the years, such as Java, Python, R, SAS, Matlab, as well as Mathematica. In addition to using off-the-shelf solutions, I developed novel AI&ML algorithms, predictive analytics, alert and recommendation systems for various industrial applications such as IoT, mobile networks, and chemometrics. I also diagnosed existing algorithms and examined their suitability for the business (and adjusted as necessary). Another service I provide is general statistical consultation (data collection, design of experiments, analysis, etc.).
Additional abilities: characterizing architectures for cloud pipelines (storage, access and analysis) of big data and implementation of state-of-the-art artificial intelligence and machine learning algorithms, both for research and production usages. Characterizing and implementing data management processes and automated data handling systems (cleaning, access, analysis, reporting), and characterizing reporting interfaces (Dashboards).
An active researcher in several fields: statistical learning for dynamic systems, measurement error models and statistical analysis of big data. Senior Lecturer in the Haifa University Department of Statistics, currently on sabbatical. In my research, I develop mathematical and statistical theory, methodology and algorithms for inference and prediction in various domains where statistical/machine learning and artificial intelligence are applied, such as biostatistics, epidemiology, and system biology. See a list of publications below. I supervise Postdoc, PhD and Master’s students.
I completed my postdoc in the Department of Mathematics and Computer Science, Eindhoven University of Technology, where I was involved in a project with Philips Research Eindhoven. I often collaborate with scientists both in Israel and abroad. One example is my collaboration with the Biostatistics & Biomathematics Unit at the Gertner Institute (a national research institute for the study of epidemiology and health policy), where we developed statistical and machine learning algorithms to better understand and predict the dynamics of infectious diseases and other biological processes.
I am perpetually involved in scientific endeavors – I often lecture at conferences and at times organize them. In 2019 I chaired the Scientific Program of the Annual Conference of the Israel Statistical Association.
I am also a member of the Israel Statistical Association Council, and Vice President of the Eastern Mediterranean Region of the International Biometric Society.
Yaari, Huppert & Dattner (2019). A statistical methodology for data-driven partitioning of infectious disease incidence into age-groups; arXiv:1907.03441.
Shabtay, Yaari, & Dattner (2019). A Guided FP-growth algorithm for multitude-targeted mining of big data; arXiv:1803.06632.
Yaari & Dattner (2019). simode: R Package for statistical inference of ordinary differential equations using separableintegral-matching; Journal of Open Source Software, 4(44), 1850, https://doi.org/10.21105/joss.01850.
Dattner & Gugushvili (2018). Application of one-step method to parameter estimation in ODE models, Statistica Neerlandica, Vol. 72, Issue 2, 126-156.
Dattner & Huppert (2018). Editorial: Modern statistical tools for inference and prediction of infectious diseases using mathematical models, Statistical Methods in Medical Research, Vol. 27, Issue 7, 1999-2014.
Yaari, Dattner & Huppert (2018). A two-stage approach for estimating the parameters of an age-group epidemic model from incidence data, Statistical Methods in Medical Research, Vol. 27, Issue 7, 1999-2014.
Vujacic & Dattner (2018). Consistency of direct integral estimator for partially observed systems of ordinary differential equations, Statistics and Probability Letters, Vol.132, 40-45.
Dattner, Miller, Petrenko, Kadouriz, Jurkevitch & Huppert (2017). Modelling and Parameter Inference of Predator-prey Dynamics in Heterogeneous Environments Using The Direct Integral Approach, Journal of The Royal Society Interface 14.126: 20160525.
Dattner, Reiss & Trabs (2016). Adaptive Quantile Estimation in Deconvolution with Unknown Error Distribution, Bernoulli,Vol. 22, No. 1, 143-192.
Dattner & Klaassen (2015). Optimal Rate of Direct Estimators in Systems of Ordinary Differential Equations Linear in Functions of the Parameters, Electronic Journal of Statistics, Vol. 9, No. 2, 1939-1973.
Vujacic, Dattner, Gonzalez, & Wit (2015). Time-Course Window Estimator for Ordinary Differential Equations Linear in the Parameters, Statistics and Computing, Vol. 25, No. 6, 1157–1170.
Dattner (2013). Deconvolution of P(X < Y) with Supersmooth Error Distributions, Statistics and Probability Letters, Vol.83, Issue 8, 1880-1887.
Dattner & Reiser (2013). Estimation of Distribution Functions in Measurement Error Models, Journal of Statistical Planning and Inference, Vol. 143, No. 3, 479–493.
Dattner, Goldenshluger & Juditsky (2011). On Deconvolution of Distribution Functions, Annals of Statistics, Vol. 39, No. 5, 2477-2501.
Dattner (2009). Statistical Properties of the Hough Transform Estimator in the Presence of Measurement Errors, Journal of Multivariate Analysis, Vol.100, No.1, 112-125.
In recent years, I fully designed and taught several courses on Statistics and Statistical/Machine learning. The courses cover both theory and application and use Python and R. One example is Statistical Analysis of Big Data, which included such topics as distributed vs ‘classical’ statistical learning, MapReduce, Hadoop and Spark, association rules (Apriori and FP-growth algorithms), recommendation systems (Collaborative Filtering), bag of little bootstraps (scalable bootstrap for big data), Stochastic Gradient Descent, imbalanced classification (using association rules, XGboost, Random Forests, logistic regression and SVM), SVD, PCA and deep learning based regression (stacked auto-encoders (SAE) and fully-connected neural network (FNN)), and more.
Feel free to contact me for teaching material and ideas.
In addition to my interest in data science, I am also a musician, always creating and recording original music – mainly jazz with modern influences. In fact, for several years, I was making a living solely from my musical career (teaching piano and performing). You can listen to some of my original music here. One special project is the album I recorded in Havana, Cuba with local musicians.