Neural networks have become a widely adopted tool for tackling a variety of problems in machine learning and artificial intelligence. In this contribution we use the mathematical framework of local stability analysis to gain a deeper understanding of the learning dynamics of feed forward neural networks. Therefore, we derive equations for the tangent operator of the learning dynamics of three-layer networks learning regression tasks. The results are valid for an arbitrary numbers of nodes and arbitrary choices of activation functions. Applying the results to a network learning a regression task, we investigate numerically, how stability indicators relate to the final training-loss. Although the specific results vary with different choices of initial conditions and activation functions, we demonstrate that it is possible to predict the final training loss, by monitoring finite-time Lyapunov exponents or covariant Lyapunov vectors during the training process.

In this paper, we introduce a novel predict-and-optimize method for profit-driven churn prevention. We frame the task of targeting customers for a retention campaign as a regret minimization problem. The main objective is to leverage individual customer lifetime values (CLVs) to ensure that only the most valuable customers are targeted. In contrast, many profit-driven strategies focus on churn probabilities while considering average CLVs. This often results in significant information loss due to data aggregation. Our proposed model aligns with the guidelines of Predict-and-Optimize (PnO) frameworks and can be efficiently solved using stochastic gradient descent methods. Results from 12 churn prediction datasets underscore the effectiveness of our approach, which achieves the best average performance compared to other well-established strategies in terms of average profit.

The cross-lingual transfer is a promising technique to solve tasks in less-resourced languages. In this empirical study, we compare two fine-tuning approaches combined with zero-shot and full-shot learning approaches for large language models in a cross-lingual setting. As fine-tuning strategies, we compare parameter-efficient adapter methods with fine-tuning of all parameters. As cross-lingual transfer strategies, we compare the intermediate-training (\textit{IT}) that uses each language sequentially and cross-lingual validation (\textit{CLV}) that uses a target language already in the validation phase of fine-tuning. We assess the success of transfer and the extent of catastrophic forgetting in a source language due to cross-lingual transfer, i.e., how much previously acquired knowledge is lost when we learn new information in a different language. The results on two different classification problems, hate speech detection and product reviews, each containing datasets in several languages, show that the \textit{IT} cross-lingual strategy outperforms \textit{CLV} for the target language. Our findings indicate that, in the majority of cases, the \textit{CLV} strategy demonstrates superior retention of knowledge in the base language (English) compared to the \textit{IT} strategy, when evaluating catastrophic forgetting in multiple cross-lingual transfers.

Abstract-- Companies across the globe are keen on targeting potential high-value customers in an attempt to expand revenue and this could be achieved only by understanding the customers more. Customer Lifetime Value (CLV) is the total monetary value of transactions/purchases made by a customer with the business over an intended period of time and is used as means to estimate future customer interactions. CLV finds application in a number of distinct business domains such as Banking, Insurance, Online-entertainment, Gaming, and E-Commerce. The existing distribution-based and basic (recency, frequency & monetary) based models face a limitation in terms of handling a wide variety of input features. Moreover, the more advanced Deep learning approaches could be superfluous and add an undesirable element of complexity in certain application areas. We, therefore, propose a system which is able to qualify both as effective, and comprehensive yet simple and interpretable. With that in mind, we develop a meta-learning-based stacked regression model which combines the predictions from bagging and boosting models that each is found to perform well individually. Empirical tests have been carried out on an openly available Online Retail dataset to evaluate various models and show the efficacy of the proposed approach. The key to flourishing businesses lies in understanding the customers using various aspects of their interactions with the businesses.

The proliferation of DTC, SaaS, and subscription-based companies has had many venture capitalists and investors to call for a better valuation strategy. Traditional DCF models have often required investors to take leaps of faith over blindspots that, according to the Retina team, can be avoided. We spoke with Retina.AI Founders Michael Greenberg (CEO) and Brad Ito (CTO) about how customer lifetime value (CLV) can be used to provide a much more accurate representation of a company's valuation than historical metrics such as a DCF. Retina urges its users to "Focus on the right customer, not the "right now" customer" by developing an incredibly intimate understanding of total predictive customer lifetime value, or the amount of money a customer will spend over the course of their lifetime. Retina's machine learning model combines recency, frequency, and magnitude (RFM), as well as churn rates to map out accurate customer journeys.

He's just become a customer of your B2B software company and agreed to buy your product, which comes with a year of support and maintenance. After 12 months, John will have to renew his contract to keep his licenses active. Now it's time to record the sale and move on to acquiring the next customer, right? With fragmented audiences, expensive advertising, and fierce competition, marketers must become more strategic in how they view customers' revenue potential. Today, once a sale is closed, many marketers consider their job (mostly) done.

Outliers is one of those issues we come across almost every day in a machine learning modelling. Wikipedia defines outliers as "an observation point that is distant from other observations." That means, some minority cases in the data set are different from the majority of the data. I would like to classify outlier data in to two main categories: Non-Natural and Natural. The non-natural outliers are those which are caused by measurement errors, wrong data collection or wrong data entry.

Did you know that 80 percent of users churn within three months of downloading an app? That's because most apps are marketed to the masses and not necessarily to the right customers. Oftentimes, the goal of app marketing is to reach as many consumers as possible with the hopes of recruiting en masse and converting at better-than-average ratios. But part of the challenge for marketers is that many of today's strategies are driven by metrics that don't link to advanced user targeting and growth. More specifically, app marketers aren't using available data strategically to deliver productive user experiences that ultimately drive greater business profitability.

Did you know that 80 percent of users churn within three months of downloading an app? That's because most apps are marketed to the masses and not necessarily to the right customers. Oftentimes, the goal of app marketing is to reach as many consumers as possible with the hopes of recruiting en masse and converting at better-than-average ratios. But part of the challenge for marketers is that many of today's strategies are driven by metrics that don't link to advanced user targeting and growth. More specifically, app marketers aren't using available data strategically to deliver productive user experiences that ultimately drive greater business profitability.

Did you know that 80 percent of users churn within three months of downloading an app? That's because most apps are marketed to the masses and not necessarily to the right customers. Oftentimes, the goal of app marketing is to reach as many consumers as possible with the hopes of recruiting en masse and converting at better-than-average ratios. But part of the challenge for marketers is that many of today's strategies are driven by metrics that don't link to advanced user targeting and growth. More specifically, app marketers aren't using available data strategically to deliver productive user experiences that ultimately drive greater business profitability.