A/B tests, or online controlled experiments, are used heavily in the software industry to evaluate implementations of ideas, as the paradigm is the gold standard in science for establishing causality: the changes introduced in the treatment caused the changes to the metrics of interest with high probability.What distinguishes software experiments, or A/B tests, from experiments in many other domains is the scale (e.g., over 100 experiment treatments may launch on a given workday in large companies) and the effect sizes that matter to the business are small (e.g., a 3% improvement to conversion rate from a single experiment is a cause for celebration).The humbling reality is that most experiments fail to improve key metrics, and success rates of only about 10-20% are most common.With low success rates, the industry standard alpha threshold of 0.05 implies a high probability of false positives.We begin with motivation about why false positives are expensive in many software domains.We then offer several approaches to estimate the true success rate of experiments, given the observed "win" rate (statistically significant positive improvements), and show examples from Expedia and Optimizely.We offer a modified procedure for experimentation, based in sequential group testing, that selectively extends experiments to reduce false positives, increase power, at a small increase to runtime.We conclude with a discussion of the difference between ideas and experiments in practice, terms that are often incorrectly used interchangeably. CCS CONCEPTS General and Reference →

A/B tests, or online controlled experiments, are heavily used in industry to evaluate implementations of ideas. While the statistics behind controlled experiments are well documented and some basic pitfalls known, we have observed some seemingly intuitive concepts being touted, including by A/B tool vendors and agencies, which are misleading, often badly so. Our goal is to describe these misunderstandings, the "intuition" behind them, and to explain and bust that intuition with solid statistical reasoning. We provide recommendations that experimentation platform designers can implement to make it harder for experimenters to make these intuitive mistakes.

The Internet provides developers of connected software, including web sites, applications, and devices, an unprecedented opportunity to accelerate innovation by evaluating ideas quickly and accurately using controlled experiments, also known as A/B tests. From front-end user-interface changes to backend algorithms, from search engines (e.g., Google, Bing, Yahoo!) to retailers (e.g., Amazon, eBay, Etsy) to social networking services (e.g., Facebook, LinkedIn, Twitter) to travel services (e.g., Expedia, Airbnb, Booking.com) to many startups, online controlled experiments are now utilized to make data-driven decisions at a wide range of companies. While the theory of a controlled experiment is simple, and dates back to Sir Ronald A. Fisher's experiments at the Rothamsted Agricultural Experimental Station in England in the 1920s, the deployment and evaluation of online controlled experiments at scale (100's of concurrently running experiments) across variety of web sites, mobile apps, and desktop applications presents many pitfalls and new research challenges. In this tutorial we will give an introduction to A/B testing, share key lessons learned from scaling experimentation at Bing to thousands of experiments per year, present real examples, and outline promising directions for future work. The tutorial will go beyond applications of A/B testing in information retrieval and will also discuss on practical and research challenges arising in experimentation on web sites and mobile and desktop apps. Our goal in this tutorial is to teach attendees how to scale experimentation for their teams, products, and companies, leading to better data-driven decisions. We also want to inspire more academic research in the relatively new and rapidly evolving field of online controlled experimentation.

Online controlled experiments (e.g., A/B tests) are now regularly used to guide product development and accelerate innovation in software. Product ideas are evaluated as scientific hypotheses, and tested on web sites, mobile applications, desktop applications, services, and operating system features. One of the key challenges for organizations that run controlled experiments is to select an Overall Evaluation Criterion (OEC), i.e., the criterion by which to evaluate the different variants. The difficulty is that short-term changes to metrics may not predict the long-term impact of a change. For example, raising prices likely increases short-term revenue but also likely reduces long-term revenue (customer lifetime value) as users abandon. Degrading search results in a Search Engine causes users to search more, thus increasing query share short-term, but increasing abandonment and thus reducing longterm customer lifetime value. Ideally, an OEC is based on metrics in a short-term experiment that are good predictors of long-term value. To assess long-term impact, one approach is to run longterm controlled experiments and assume that long-term effects are represented by observed metrics. In this paper we share several examples of long-term experiments and the pitfalls associated with running them. We discuss cookie stability, survivorship bias, selection bias, and perceived trends, and share methodologies that can be used to partially address some of these issues. While there is clearly value in evaluating long-term trends, experimenters running long-term experiments must be cautious, as results may be due to the above pitfalls more than the true delta between the Treatment and Control. We hope our real examples and analyses will sensitize readers to the issues and encourage the development of new methodologies for this important problem.

The Internet provides developers of connected software, including web sites, applications, and devices, an unprecedented opportunity to accelerate innovation by evaluating ideas quickly and accurately using trustworthy controlled experiments (e.g., A/B tests and their generalizations). From front-end user-interface changes to backend recommendation systems and relevance algorithms, from search engines (e.g., Google, Microsoft's Bing, Yahoo) to retailers (e.g., Amazon, eBay, Netflix, Etsy) to social networking services (e.g., Facebook, LinkedIn, Twitter) to Travel services (e.g., Expedia, Airbnb, Booking.com) to many startups, online controlled experiments are now utilized to make data-driven decisions at a wide range of companies. While the theory of a controlled experiment is simple, and dates back to Sir Ronald A. Fisher's experiments at the Rothamsted Agricultural Experimental Station in England in the 1920s, the deployment and mining of online controlled experiments at scale (e.g., hundreds of experiments run every day at Bing) and deployment of online controlled experiments across dozens of web sites and applications has taught us many lessons. We provide an introduction, share real examples, key lessons, and cultural challenges.

Web site owners, from small web sites to the largest properties that include Amazon, Facebook, Google, LinkedIn, Microsoft, and Yahoo, attempt to improve their web sites, optimizing for criteria ranging from repeat usage, time on site, to revenue. Having been involved in running thousands of controlled experiments at Amazon, Booking.com, LinkedIn, and multiple Microsoft properties, we share seven rules of thumb for experimenters, which we have generalized from these experiments and their results. These are principles that we believe have broad applicability in web optimization and analytics outside of controlled experiments, yet they are not provably correct, and in some cases exceptions are known.

Web-facing companies, including Amazon, eBay, Etsy, Facebook, Google, Groupon, Intuit, LinkedIn, Microsoft, Netflix, Shop Direct, StumbleUpon, Yahoo, and Zynga use online controlled experiments to guide product development and accelerate innovation. At Microsoft's Bing, the use of controlled experiments has grown exponentially over time, with over 200 concurrent experiments now running on any given day. Running experiments at large scale requires addressing multiple challenges in three areas: cultural/organizational, engineering, and trustworthiness. On the cultural and organizational front, the larger organization needs to learn the reasons for running controlled experiments and the tradeoffs between controlled experiments and other methods of evaluating ideas. We discuss why negative experiments, which degrade the user experience short term, should be run, given the learning value and long-term benefits. On the engineering side, we architected a highly scalable system, able to handle data at massive scale: hundreds of concurrent experiments, each containing millions of users. Classical testing and debugging techniques no longer apply when there are billions of live variants of the site, so alerts are used to identify issues rather than relying on heavy up-front testing. On the trustworthiness front, we have a high occurrence of false positives that we address, and we alert experimenters to statistical interactions between experiments. The Bing Experimentation System is credited with having accelerated innovation and increased annual revenues by hundreds of millions of dollars, by allowing us to find and focus on key ideas evaluated through thousands of controlled experiments. A 1% improvement to revenue equals more than $10M annually in the US, yet many ideas impact key metrics by 1% and are not well estimated a-priori. The system has also identified many negative features that we avoided deploying, despite key stakeholders' early excitement, saving us similar large amounts.

Online controlled experiments are at the heart of making data-driven decisions at a diverse set of companies, including Amazon, eBay, Facebook, Google, Microsoft, Yahoo, and Zynga. Small differences in key metrics, on the order of fractions of a percent, may have very significant business implications. At Bing it is not uncommon to see experiments that impact annual revenue by millions of dollars, even tens of millions of dollars, either positively or negatively. With thousands of experiments being run annually, improving the sensitivity of experiments allows for more precise assessment of value, or equivalently running the experiments on smaller populations (supporting more experiments) or for shorter durations (improving the feedback cycle and agility). We propose an approach (CUPED) that utilizes data from the pre-experiment period to reduce metric variability and hence achieve better sensitivity. This technique is applicable to a wide variety of key business metrics, and it is practical and easy to implement. The results on Bing's experimentation system are very successful: we can reduce variance by about 50%, effectively achieving the same statistical power with only half of the users, or half the duration.

Online controlled experiments are often utilized to make data-driven decisions at Amazon, Microsoft, eBay, Facebook, Google, Yahoo, Zynga, and at many other companies. While the theory of a controlled experiment is simple, and dates back to Sir Ronald A. Fisher's experiments at the Rothamsted Agricultural Experimental Station in England in the 1920s, the deployment and mining of online controlled experiments at scale--thousands of experiments now--has taught us many lessons. These exemplify the proverb that the difference between theory and practice is greater in practice than in theory. We present our learnings as they happened: puzzling outcomes of controlled experiments that we analyzed deeply to understand and explain. Each of these took multiple-person weeks to months to properly analyze and get to the often surprising root cause. The root causes behind these puzzling results are not isolated incidents; these issues generalized to multiple experiments. The heightened awareness should help readers increase the trustworthiness of the results coming out of controlled experiments. At Microsoft's Bing, it is not uncommon to see experiments that impact annual revenue by millions of dollars, thus getting trustworthy results is critical and investing in understanding anomalies has tremendous payoff: reversing a single incorrect decision based on the results of an experiment can fund a whole team of analysts. The topics we cover include: the OEC (Overall Evaluation Criterion), click tracking, effect trends, experiment length and power, and carryover effects.

The web provides an unprecedented opportunity to accelerate innovation by evaluating ideas quickly and accurately using controlled experiments (e.g., A/B tests and their generalizations). Whether for front-end user-interface changes, or backend recommendation systems and relevance algorithms, online controlled experiments are now utilized to make data-driven decisions at Amazon, Microsoft, eBay, Facebook, Google, Yahoo, Zynga, and at many other companies. While the theory of a controlled experiment is simple, and dates back to Sir Ronald A. Fisher's experiments at the Rothamsted Agricultural Experimental Station in England in the 1920s, the deployment and mining of online controlled experiments at scale--thousands of experiments now--has taught us many lessons. We provide an introduction, share real examples, key learnings, cultural challenges, and humbling statistics.

Controlled experiments, also called randomized experiments and A/B tests, have had a profound influence on multiple fields, including medicine, agriculture, manufacturing, and advertising. While the theoretical aspects of offline controlled experiments have been well studied and documented, the practical aspects of running them in online settings, such as web sites and services, are still being developed. As the usage of controlled experiments grows in these online settings, it is becoming more important to understand the opportunities and pitfalls one might face when using them in practice. A survey of online controlled experiments and lessons learned were previously documented in Controlled Experiments on the Web: Survey and Practical Guide (Kohavi, et al., 2009). In this follow-on paper, we focus on pitfalls we have seen after running numerous experiments at Microsoft. The pitfalls include a wide range of topics, such as assuming that common statistical formulas used to calculate standard deviation and statistical power can be applied and ignoring robots in analysis (a problem unique to online settings). Online experiments allow for techniques like gradual ramp-up of treatments to avoid the possibility of exposing many customers to a bad (e.g., buggy) Treatment. With that ability, we discovered that it's easy to incorrectly identify the winning Treatment because of Simpson's paradox.

The web provides an unprecedented opportunity to evaluate ideas quickly using controlled experiments, also called randomized experiments, A/B tests (and their generalizations), split tests, Control/Treatment tests, MultiVariable Tests (MVT) and parallel flights. Controlled experiments embody the best scientific design for establishing a causal relationship between changes and their influence on user-observable behavior. We provide a practical guide to conducting online experiments, where end-users can help guide the development of features. Our experience indicates that significant learning and return-on-investment (ROI) are seen when development teams listen to their customers, not to the Highest Paid Person’s Opinion (HiPPO). We provide several examples of controlled experiments with surprising results. We review the important ingredients of running controlled experiments, and discuss their limitations (both technical and organizational). We focus on several areas that are critical to experimentation, including statistical power, sample size, and techniques for variance reduction. We describe common architectures for experimentation systems and analyze their advantages and disadvantages. We evaluate randomization and hashing techniques, which we show are not as simple in practice as is often assumed. Controlled experiments typically generate large amounts of data, which can be analyzed using data mining techniques to gain deeper understanding of the factors influencing the outcome of interest, leading to new hypotheses and creating a virtuous cycle of improvements. Organizations that embrace controlled experiments with clear evaluation criteria can evolve their systems with automated optimizations and real-time analyses. Based on our extensive practical experience with multiple systems and organizations, we share key lessons that will help practitioners in running trustworthy controlled experiments.

The web provides an unprecedented opportunity to evaluate ideas quickly using controlled experiments, also called randomized experiments (single factor or factorial designs), A/B tests (and their generalizations), split tests, Control/Treatment tests, and parallel flights. Controlled experiments embody the best scientific design for establishing a causal relationship between changes and their influence on user-observable behavior. We provide a practical guide to conducting online experiments, where end-users can help guide the development of features. Our experience indicates that significant learning and return-on-investment (ROI) are seen when development teams listen to their customers, not to the Highest Paid Person's Opinion (HiPPO). We provide several examples of controlled experiments with surprising results. We review the important ingredients of running controlled experiments, and discuss their limitations (both technical and organizational). We focus on several areas that are critical to experimentation, including statistical power, sample size, and techniques for variance reduction. We describe common architectures for experimentation systems and analyze their advantages and disadvantages. We evaluate randomization and hashing techniques, which we show are not as simple in practice as is often assumed. Controlled experiments typically generate large amounts of data, which can be analyzed using data mining techniques to gain deeper understanding of the factors influencing the outcome of interest, leading to new hypotheses and creating a virtuous cycle of improvements. Organizations that embrace controlled experiments with clear evaluation criteria can evolve their systems with automated optimizations and real-time analyses. Based on our extensive practical experience with multiple systems and organizations, we share key lessons that will help practitioners in running trustworthy controlled experiments.

Segmentation based on RFM (Recency, Frequency, and Monetary) has been used for over 50 years by direct marketers to target a subset of their customers, save mailing costs, and improve profits. RFM analysis is commonly performed using the Arthur Hughes method, which bins each of the three RFM attributes independently into five equal frequency bins. The resulting 125 cells are depicted in a tabular format or as bar graphs and analyzed by marketers, who determine the best cells (customer segments) to target. We propose an interactive visualization of RFM that helps marketers visualize and quickly identify important customer segments. Additionally, we show an integrated filtering approach that allows marketers to interactively explore the RFM segments in relation to other customer attributes, such as behavioral or demographic, to identify interesting sub-segments in the customer base. We depict these RFM visualizations on two large real-world data sets and discuss how customers have used these visualizations in practice to glean interesting insights from their data. Given, the widespread use of RFM as a critical, and many times the only, segmentation tool, we believe that the proposed intuitive and interactive visualization will provide significant business value.

We show that the e-commerce domain can provide all the right ingredients for successful data mining. We describe an integrated architecture for supporting this integration. The architecture can dramatically reduce the pre-processing, cleaning, and data understanding effort often documented to take 80% of the time in knowledge discovery projects. We emphasize the need for data collection at the application server layer (not the Web server) in order to support logging of data and metadata that is essential to the discovery process. We describe the data transformation bridges required from the transaction processing systems and customer event streams (e.g., clickstreams) to the data warehouse. We detail the mining workbench, which needs to provide multiple views of the data through reporting, data mining algorithms, visualization, and OLAP. We conclude with a set of challenges.

Organizations conducting Electronic Commerce (e-commerce) can greatly benefit from the insight that data mining of transactional and clickstream data provides. Such insight helps not only to improve the electronic channel (e.g., a web site), but it is also a learning vehicle for the bigger organization conducting business at brick-and-mortar stores. The e-commerce site serves as an early alert system for emerging patterns and a laboratory for experimentation. For successful data mining, several ingredients are needed and e-commerce provides all the right ones (the Good). Web server logs, which are commonly used as the source of data for mining e-commerce data, were designed to debug web servers, and the data they provide is insufficient, requiring the use of heuristics to reconstruct events. Moreover, many events are never logged in web server logs, limiting the source of data for mining (the Bad). Many of the problems of dealing with web server log data can be resolved by properly architecting the e-commerce sites to generate data needed for mining. Even with a good architecture, however, there are challenging problems that remain hard to solve (the Ugly). Lessons and metrics based on mining real e-commerce data are presented.

This study compares five well-known association rule algorithms using three real-world datasets and an artificial dataset. The experimental results confirm the performance improvements previously claimed by the authors on the artificial data, but some of these gains do not carry over to the real datasets, indicating overfitting of the algorithms to the IBM artificial dataset. More importantly, we found that the choice of algorithm only matters at support levels that generate more rules than would be useful in practice. For support levels that generate less than 1,000,000 rules, which is much more than humans can handle and is sufficient for prediction purposes where data is loaded into RAM, Apriori finishes processing in less than 10 minutes. On our datasets, we observed super-exponential growth in the number of rules. On one of our datasets, a 0.02% change in the support increased the number of rules from less than a million to over a billion, implying that outside a very narrow range of support values, the choice of algorithm is irrelevant.

No abstract available.

Data mining algorithms including machine learning, statistical analysis, and pattern recognition techniques can greatly improve our understanding of data warehouses that are now becoming more widespread. In this paper, we focus on classification algorithms and review the need for multiple classification algorithms. We describe a system called /spl Mscr//spl Lscr//spl Cscr/++ which was designed to help choose the appropriate classification algorithm for a given dataset by making it easy to compare the utility of different algorithms on a specific dataset of interest. /spl Mscr//spl Lscr//spl Cscr/++ not only provides a work-bench for such comparisons, but also provides a library of C++ classes to aid in the development of new algorithms, especially hybrid algorithms and multi-strategy algorithms. Such algorithms are generally hard to code from scratch. We discuss design issues, interfaces to other programs, and visualization of the resulting classifiers.

We present MLC++, a library of C++ classes and tools for supervised machine learning. While MLC++ provides general learning algorithms that can be used by end users, the main objective is to provide researchers and experts with a wide variety of tools that can accelerate algorithm development, increase software reliability, provide comparison tools, and display information visually. More than just a collection of existing algorithms, MLC++ is can attempt to extract commonalities of algorithms and decompose them for a unified view that is simple, coherent, and extensible. In this paper we discuss the problems MLC++ aims to solve, the design of MLC++, and the current functionality.>