In recent years, with the rapid development of artificial intelligence and social media, the influence of word-of-mouth (WOM) on the diffusion of online content has become increasingly evident. Video platforms can use artificial intelligence to collect WOM data of programs and formulate corresponding pricing strategies. Based on this background, considering the impact of online WOM effects on the diffusion of on-demand content exclusive to members, this study constructs a two-stage product provision model for online video platforms, consisting of the premiere and follow-up broadcast stage. Based on expected utility theory, this research explores the pricing strategies for member-exclusive on-demand content under two profit models and analyzes the influence of program WOM attributes and program quality on optimal decision-making. The findings reveal that: When the premiere stage WOM for a program is either highly positive or negative, video platform should adopt an "advertising-dominant strategy". When the premiere stage WOM is moderate, a " fee-dominant strategy" is preferable. Higher program quality increases the platform's inclination toward the "fee-dominant strategy". The better the premiere stage WOM and program quality, the more users tend to watch during the premiere stage. Accordingly, both the program price and the platform's expected profit will vary to different degrees depending on these conditions.

With the prevalent adoption of blockchain in the financial system, there has been an increase in phishing scams on cryptocurrency platforms such as Ethereum, and an effective anomaly detection method is urgently required. The latest studies have focused on anomaly identification using natural language processing techniques or constructing simple static graphs. However, the existing methods are insufficient to convey the diversity of connectivity patterns in the Ethereum transaction network concerning amount and time. To this end, we proposed a novel transaction network embedding algorithm transE based on the multi-channel random walk to model the detection of Ethereum phishing scam accounts as a multigraph node classification task. Specifically, we first model the Ethereum transaction as a time-amount directed multigraph. Then, the hybrid feature representation of network nodes is learned via transE from their local and global neighbours, which uses the attention mechanism to maximize the probability of preserving node network neighbours. Ultimately, we employ visualization techniques and machine learning models to validate the effectiveness of the algorithms, and the model with the top performance is picked for Ethereum account classification. Experimental results indicate that the embedding vector extracted by transE improves the detection accuracy of Ethereum phishing accounts in the different classification tasks.

I plan to talk about a few big challenges we have at LinkedIn in the space of Data Science. The ones coming to my mind are (1) Measuring long-term impact; (2) Learning while preserving privacy; (3) Fairness. I can also touch upon productivity and efficiency -- which is a very practical challenge I'm sure all DS organizations face.

We have seen a massive growth of online experiments at Internet companies. Although conceptually simple, A/B tests can easily go wrong in the hands of inexperienced users and on an A/B testing platform with little governance. An invalid A/B test hurts the business by leading to non-optimal decisions. Therefore, it is now more important than ever to create an intelligent A/B platform that democratizes A/B testing and allows everyone to make quality decisions through built-in detection and diagnosis of invalid tests. In this paper, we share how we mined through historical A/B tests and identified the most common causes for invalid tests, ranging from biased design, self-selection bias to attempting to generalize A/B test result beyond the experiment population and time frame. Furthermore, we also developed scalable algorithms to automatically detect invalid A/B tests and diagnose the root cause of invalidity. Surfacing up invalidity not only improved decision quality, but also served as a user education and reduced problematic experiment designs in the long run.

Controlled experimentation, also called A/B testing, is widely adopted to accelerate product innovations in the online world. However, how fast we innovate can be limited by how we run experiments. Most experiments go through a "ramp up" process where we gradually increase the traffic to the new treatment to 100%. We have seen huge inefficiency and risk in how experiments are ramped, and it is getting in the way of innovation. This can go both ways: we ramp too slowly and much time and resource is wasted; or we ramp too fast and suboptimal decisions are made. In this paper, we build up a ramping framework that can effectively balance among Speed, Quality and Risk (SQR). We start out by identifying the top common mistakes experimenters make, and then introduce the four SQR principles corresponding to the four ramp phases of an experiment. To truly scale SQR to all experiments, we develop a statistical algorithm that is embedded into the process of running every experiment to automatically recommend ramp decisions. Finally, to complete the whole picture, we briefly cover the auto-ramp engineering infrastructure that can collect inputs and execute on the recommendations timely and reliably.

Randomized experiments, or A/B tests, are the standard approach for evaluating the causal effects of new product features, i.e., treatments. The validity of these tests rests on the "stable unit treatment value assumption" (SUTVA), which implies that the treatment only affects the behavior of treated users, and does not affect the behavior of their connections. Violations of SUTVA, common in features that exhibit network effects, result in inaccurate estimates of the causal effect of treatment. In this paper, we leverage a new experimental design for testing whether SUTVA holds, without making any assumptions on how treatment effects may spill over between the treatment and the control group. To achieve this, we simultaneously run both a completely randomized and a cluster-based randomized experiment, and then we compare the difference of the resulting estimates. We present a statistical test for measuring the significance of this difference and offer theoretical bounds on the Type I error rate. We provide practical guidelines for implementing our methodology on large-scale experimentation platforms. Importantly, the proposed methodology can be applied to settings in which a network is not necessarily observed but, if available, can be used in the analysis. Finally, we deploy this design to LinkedIn's experimentation platform and apply it to two online experiments, highlighting the presence of network effects and bias in standard A/B testing approaches in a real-world setting.

We have seen an explosive growth of mobile usage, particularly on mobile apps. It is more important than ever to be able to properly evaluate mobile app release. A/B testing is a standard framework to evaluate new ideas. We have seen much of its applications in the online world across the industry [9,10,12]. Running A/B tests on mobile apps turns out to be quite different, and much of it is attributed to the fact that we cannot ship code easily to mobile apps other than going through a lengthy build, review and release process. Mobile infrastructure and user behavior differences also contribute to how A/B tests are conducted differently on mobile apps, which will be discussed in details in this paper. In addition to measuring features individually in the new app version through randomized A/B tests, we have a unique opportunity to evaluate the mobile app as a whole using the quasi-experimental framework [21]. Not all features can be A/B tested due to infrastructure changes and wholistic product redesign. We propose and establish quasi-experimental techniques for measuring impact from mobile app release, with results shared from a recent major app launch at LinkedIn.

A/B testing, also known as bucket testing, split testing, or controlled experiment, is a standard way to evaluate user engagement or satisfaction from a new service, feature, or product. It is widely used among online websites, including social network sites such as Facebook, LinkedIn, and Twitter to make data-driven decisions. At LinkedIn, we have seen tremendous growth of controlled experiments over time, with now over 400 concurrent experiments running per day. General A/B testing frameworks and methodologies, including challenges and pitfalls, have been discussed extensively in several previous KDD work [7, 8, 9, 10]. In this paper, we describe in depth the experimentation platform we have built at LinkedIn and the challenges that arise particularly when running A/B tests at large scale in a social network setting. We start with an introduction of the experimentation platform and how it is built to handle each step of the A/B testing process at LinkedIn, from designing and deploying experiments to analyzing them. It is then followed by discussions on several more sophisticated A/B testing scenarios, such as running offline experiments and addressing the network effect, where one user's action can influence that of another. Lastly, we talk about features and processes that are crucial for building a strong experimentation culture.

A/B testing, also known as bucket testing, split testing, or controlled experiment, is a standard way to evaluate user engagement or satisfaction from a new service, feature, or product. It is widely used in online websites, including social network sites such as Facebook, LinkedIn, and Twitter to make data-driven decisions. The goal of A/B testing is to estimate the treatment effect of a new change, which becomes intricate when users are interacting, i.e., the treatment effect of a user may spill over to other users via underlying social connections.When conducting these online controlled experiments, it is a common practice to make the Stable Unit Treatment Value Assumption (SUTVA) that each individual's response is affected by their own treatment only. Though this assumption simplifies the estimation of treatment effect, it does not hold when network interference is present, and may even lead to wrong conclusion.

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.

In this workshop, we have several leading industry experts sharing their knowledge and experiences on how online controlled experiments are used in their applications. The individual talks are followed by a panel discussion.

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.

This paper deals with a new approach based on Q -learning for solving the problem of mobile robot path planning in complex unknown static environments. As a computational approach to learning through interaction with the environment, reinforcement learning algorithms have been widely used for intelligent robot control, especially in the field of autonomous mobile robots. However, the learning process is slow and cumbersome. For practical applications, rapid rates of convergence are required. Aiming at the problem of slow convergence and long learning time for Q -learning based mobile robot path planning, a state-chain sequential feedback Q -learning algorithm is proposed for quickly searching for the optimal path of mobile robots in complex unknown static environments. The state chain is built during the searching process. After one action is chosen and the reward is received, the Q -values of the state-action pairs on the previously built state chain are sequentially updated with one-step Q -learning. With the increasing number of Q -values updated after one action, the number of actual steps for convergence decreases and thus, the learning time decreases, where a step is a state transition. Extensive simulations validate the efficiency of the newly proposed approach for mobile robot path planning in complex environments. The results show that the new approach has a high convergence speed and that the robot can find the collision-free optimal path in complex unknown static environments with much shorter time, compared with the one-step Q -learning algorithm and the Q ( λ )-learning algorithm.

Edge detection and enhancement techniques are usually used in identifying the boundary of geologic bodies using potential field data. In this paper, we present an igneous rocks identification method using full gradient of potential field based on discrete cosine transform. Rocks physical properties for igneous rocks usually have high-density and high magnetic susceptibility, with strong gravity or magnetic anomaly. So it's available to identify the boundaries and distribution of igneous rocks using full gradient of gravity and magnetic anomalies method. Discrete cosine transform was used in computing full gradient of potential field to improve the computational speed and accuracy. The modeling test proves good results based on the method we have discussed. Using this method, we identified igneous rocks distribution of northwestern South China Sea and its adjacent regions.

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 CUR decomposition provides an approximation of a matrix X that has low reconstruction error and that is sparse in the sense that the resulting approximation lies in the span of only a few columns of X. In this regard, it appears to be similar to many sparse PCA methods. However, CUR takes a randomized algorithmic approach whereas most sparse PCA methods are framed as convex optimization problems. In this paper, we try to understand CUR from a sparse optimization viewpoint. In particular, we show that CUR is implicitly optimizing a sparse regression objective and, furthermore, cannot be directly cast as a sparse PCA method. We observe that the sparsity attained by CUR possesses an interesting structure, which leads us to formulate a sparse PCA method that achieves a CUR-like sparsity.

We consider experiments to measure the quality of a web search algorithm based on how much total time users take to complete assigned search tasks using that algorithm. We first analyze our data to verify that there is in fact a negative relationship between a user's total search time and a user's satisfaction for the types of tasks under consideration. Secondly, we fit a model with the user's total search time as the response to compare two different search algorithms. Finally, we propose an alternative experimental design which we demonstrate to be a substantial improvement over our current design in terms of variance reduction and efficiency.

We present a logs-based comparison of search patterns across three platforms: computers, iPhones and conventional phones. Our goal is to understand how search users differ from computer-based search users, and we focus heavily on the distribution and variability of tasks that users perform from each platform. The results suggest that search usage is much more focused for the average user than for the average computer-based user. However, search behavior on high-end phones resembles computer-based search behavior more so than search behavior. A wide variety of implications follow from these findings. First, there is no single search interface which is suitable for all phones. We suggest that for the higher-end phones, a close integration with the standard computer-based interface (in terms of personalization and available feature set) would be beneficial for the user, since these phones seem to be treated as an extension of the users' computer. For all other phones, there is a huge opportunity for personalizing the search experience for the user's mobile needs, as these users are likely to repeatedly search for a single type of information need on their phone.

We introduce a geographical adaptive fidelity (GAF) algorithm that reduces energy consumption in ad hoc wireless networks. GAF conserves energy by identifying nodes that are equivalent from a routing perspective and then turning off unnecessary nodes, keeping a constant level of routing fidelity. GAF moderates this policy using application- and system-level information; nodes that source or sink data remain on and intermediate nodes monitor and balance energy use. GAF is independent of the underlying ad hoc routing protocol; we simulate GAF over unmodified AODV and DSR. Analysis and simulation studies of GAF show that it can consume 40% to 60% less energy than an unmodified ad hoc routing protocol. Moreover, simulations of GAP suggest that network lifetime increases proportionally to node density; in one example, a four-fold increase in node density leads to network lifetime increase for 3 to 6 times (depending on the mobility pattern). More generally, GAF is an example of adaptive fidelity, a technique proposed for extending the lifetime of self-configuring systems by exploiting redundancy to conserve energy while maintaining application fidelity.