From an ecosystem perspective, mergers and acquisitions (M&A) are one of the key paths for firms to foster complementary sectors and gain complementary assets. From the perspective of sustainable development, M&A can reallocate resources from target to asset to achieve better synergy and prolong the operation of a merged firm. However, M&A activities are characterized by high risk due to the high cost and uncertainty. Thus, a prediction model of M&A decisions is valuable for firms’ strategy design from an ecosystem and sustainable development perspective. By adopting a machine learning technique, this study measured the cross-border M&A decisions by analyzing firm-level cross-sectional data of the global financial marketplace under ecosystem mapping for the application of various country, deal and firm-level indicators related to sustainable development. Our paper can support the hypotheses of corporate governance, ecosystem stakeholder theory, ecosystem risk and institution theory in explaining that firms can increase their success rate of M&A to achieve sustainable development. Methodologically, we used AdaBoost to train several weak classifiers (decision trees) to achieve a strong decision-making model with a large financial transaction database of 215,160 deal activities. Results achieved 80.1% prediction accuracy by using the AdaBoost model through 10-fold cross validation. We found that differences exist on prediction features of M&A with different characteristics of sustainable development. For a robustness check, comparable results were obtained with a support vector machine (SVM) model. By analyses of the features during the cross-border M&A decision-making processing, this study is expected to contribute to the utilization of machine learning in ecosystem studies.

The action recognition based on local spatial-temporal feature has attracted more and more attentions. The codebook used in the recognition is usually generated by k-means and the code words are considered to have the same importance. But in fact, it isn’t true. So in this paper, we propose two strategies to measure the importance of different code words and improve the HIK-Kmeans algorithm .The experiment result shows that our improved algorithm increases the accuracy of action recognition.

The main challenge of Topic Detection and Tracking (TDT) for Blog is the insufficient information in a topic description and the lack of key words input by users. We propose a Two-layer KL Distance approach which combines the KL distance model with a lexical semantic association matrix model. First, the KL Distance model captured the weights of Initial feature words. Second, the KL Distance model was used again to estimate weights of words linked with initial feature words in the lexical Semantic Association Matrix. Extensive experiments show the advantages of our method over the baselines as well as the effectiveness of the two-layer of KL Distance.

The purpose of Fast track project management technique is done to reduce the project time by overlapping the project design and construction phases and thereby by making maximum possible activities run parallel to each other so as to reduce the time. The main aim is to study of fast tracking process of a real estate project. And to evolve fast tracking model based on dependency structure matrix. As engineering activities are interdependent and sequenced based on information flows, modeling information exchange for these activities is impossible with CPM or PERT. Researcher have investigated the dependency structure matrix as a tool to identify and manage information exchange between activities. In the Ahmedabad city, most of the mega infrastructure project are delay due to some technical or financial reason. So that, there are major losses in time and project cannot complete within its time period. For these project, time is real money. So, fast tracking is one of the appropriate options to take project on its proper track. Thus, DSM is very important model to fast track project at any panic Situation. It has also used prediction model to calculate rework of days for succeeding activity.