Automatic Identification and Classification of Share Buybacks and their Effect on Short-, Mid- and Long-Term Returns

  title={Automatic Identification and Classification of Share Buybacks and their Effect on Short-, Mid- and Long-Term Returns},
  author={Thilo Reintjes},
This thesis investigates share buybacks, specifically share buyback announcements. It addresses how to recognize such announcements, the excess return of share buybacks, and the prediction of returns after a share buyback announcement. To achieve this, this thesis discusses ways to filter out share buyback announcements from an incoming news flow, analyze them and train a variety of machine learning models to predict future returns. For this purpose, we illustrate two natural language… 



Do corporate insiders use stock buybacks for personal gain?

ABSTRACT This paper investigates the hypothesis of whether corporate insiders sell their own personal shareholdings more frequently when they are executing stock buybacks using corporate funds. I

Stock Buybacks: Good Or Bad For Investors?

A recent news flash announced that Warren Buffet’s Berkshire Hathaway would buy back $1.2 billion worth of its own Class A stock. In recent times, such stock buybacks are happening in rapid

Are Buybacks Increasing EPS?

Trends indicate that treasury shares or buyback shares are gaining new momentum and intensity and maybe effecting reported earnings per share. This study was undertaken by evaluating the buyback

Open-market stock repurchases as signals for earnings and risk changes

Attention is All you Need

A new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely is proposed, which generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.

Adaptive computation and machine learning

This book attempts to give an overview of the different recent efforts to deal with covariate shift, a challenging situation where the joint distribution of inputs and outputs differs between the training and test stages.

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.

LightGBM: A Highly Efficient Gradient Boosting Decision Tree

It is proved that, since the data instances with larger gradients play a more important role in the computation of information gain, GOSS can obtain quite accurate estimation of the information gain with a much smaller data size, and is called LightGBM.

XGBoost: A Scalable Tree Boosting System

This paper proposes a novel sparsity-aware algorithm for sparse data and weighted quantile sketch for approximate tree learning and provides insights on cache access patterns, data compression and sharding to build a scalable tree boosting system called XGBoost.

Random Forests

Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.