Purpose -This paper seeks to develop a model for risk management of knowledge loss in a project-based organization in Iran. Design/methodology/approach -This study uses a multi-stage research approach. In the first stage, existing practices are examined to develop a model for risk management of knowledge loss. In the second stage, the model is evaluated by testing it in a case study. The methods integrated as the foundations of the Integrated KM and RM model are: the PMBOK risk management (RM) approach, the Fraunhofer IPK knowledge management (KM) model, and the TVA knowledge risk assessment framework. Findings -The analytical approach includes a six-step integrated model that manages the risk of critical knowledge in the case study. The results show that, after a year of implementing the model, the job positions facing knowledge loss were reduced by 88 percent.Research limitations/implications -The integrated KM and RM model can be used to assist the planning, establishment and evaluation of knowledge loss in projects. This helps to ensure that key issues regarding knowledge loss are covered during the planning and implementation phases of project management. Originality/value -This study provides an integrated perspective of KM in project-based organizations. It offers valuable guidelines that can help decision makers consider key issues during a risk assessment of knowledge factors in project management. Outputs of this model can prepare an extensive assessment report about the risk of knowledge loss in a project-based organization with suggestions for preservation plans to mitigate its effects.

Purpose -The main aim of this paper is to study the effects of organizational culture on environmental responsiveness capability (ERC), both directly and through the mediation of knowledge management (KM) in selected Iranian Industrial Research Organizations (IIRO). Furthermore, the effects of four types of organizational culture on ERC and KM in the target population are compared. Design/methodology/approach -Relationships between the ERC, KM and organizational culture are considered using survey data through the structural equation modelling approach. Five-point Likert questionnaire has been used as a tool for measuring variables. The authors sample includes 276 members of 13 selected target organizations whose names are not mentioned due to prior agreement. Findings -Results show that organizational culture has a positive and significant relationship with ERC, both directly and indirectly through the mediation of KM. Additionally, compared with other types of organizational cultures, innovativeness culture has the highest correlation with ERC, both directly and through KM as a mediating variable. Furthermore, cooperativeness culture has a direct significant relationship with ERC, whereas consistency and effectiveness cultures indirectly have significant and positive relationships with ERC through KM. Therefore, results of this research provide appropriate evidence that ERC can be affected directly by innovativeness culture and KM. Originality/value -The advantage of this paper compared to other related research is to study on ERC based on cultural and knowledge-related variables. Hence, it can extend the literature of ERC, and it can be useful for the managers who are dealing with industrial research company.

No abstract

Intrusion Detection Systems have considerable importance in preventing security threats and protecting computer networks against attackers. So far, various classification approaches using data mining and machine learning techniques have been proposed to the problem of intrusion detection. However, using single classifier systems for intrusion detection suffers from some limitations including lower detection rate for low-frequent attacks, detection instability, and complexity in training process. Ensemble classifier systems combine several individual classifiers and obtain a classifier with higher performance. In this paper, we propose a new ensemble classifier using Radial Basis Function (RBF) neural networks and fuzzy clustering in order to increase detection accuracy and stability, reduce false positives, and provide higher detection rate for low-frequent attacks. We also use a hybrid combination method to aggregate the individual predictions of the base classifiers, which helps to increase detection accuracy. The experimental results on NSL-KDD data set demonstrate that our proposed system has a higher detection accuracy compared to other wellknown classification systems. It also performs more effectively for detection of low-frequent attacks. Furthermore, the proposed ensemble method offers better performance compared to popular ensemble methods.

PurposeThe objective of this paper is to develop a model for planning and establishment of knowledge management (KM) strategy in one of the Iranian Sub‐stream Aerospace Industries Organization to improve company's performance.Design/methodology/approachThis research tries to use multi‐method approach by integrating balanced score card, which is a renowned strategic management approach, and Nonaka and colleagues' knowledge creation process (socialization, externalization, combination, and internalization model), which is a well‐known knowledge creation and conversion model, being adopted as the foundations of strategic knowledge management model (SKMM).FindingsThe analytical approach identifies eight issues as critical success factors of the knowledge strategy map in this case study. The overall results from the case study are positive as well, thus reflecting the appropriateness of the suggested SKMM model.Research limitations/implicationsSKMM can be used to help forward the plan, establishment and evaluation of KM strategies and initiatives. This helps to ensure that the essential issues are covered during design and implementation phases of KM strategies.Originality/valueThis paper further provides an integrated perspective of KM metrics in high‐tech industries including the aerospace industry. It gives valuable information and guidelines that hopefully will help leaders to consider important issues during performance measurement of KM strategies in organizations.

Sales forecasting is very beneficial to most businesses. A successful business needs accurate sales forecasting to understand the market and sales trends. This paper presents a novel sales forecasting model by integrating support vector regression (SVR) and bat algorithm (BA). Since the accuracy of SVR forecasting mainly depends on SVR parameters, we use BA for tuning these parameters because Bat is a newly introduced algorithm and has many parameters. In order to find the best set of BA parameters Taguchi method was utilized. We validated our model on four known UCI datasets. Then we applied our model in printed circuit board (PCB) sales forecasting case study. We compared the accuracy of the proposed model with Genetic algorithm (GA)–SVR, particle swarm optimization (PSO)–SVR, and classic-SVR. The experimental results show that the proposed model outperforms the others. To ensure the robustness of our proposed model, sensitivity analysis was also done using our model to find out the effects of dependent variables values on sales time series.

No abstract

The aim of direct marketing is to¯nd the right customers who are most likely to respond to marketing campaign messages. In order to detect which customers are most valuable, response modeling is used to classify customers as respondent or non-respondent using their purchase history information or other behavioral characteristics. Data mining techniques, including e®ective classi¯cation methods, can be used to predict responsive customers. However, the inherent problem of imbalanced data in response modeling brings some di±culties into response prediction. As a result, the prediction models will be biased towards non-respondent customers. Another problem is that single models cannot provide the desired high accuracy due to their internal limitations. In this paper, we propose an ensemble classi¯cation method which removes imbalance in the data, using a combination of clustering and under-sampling. The predictions of multiple classi¯ers are combined in order to achieve better results. Using data from a bank's marketing campaigns, this ensemble method is implemented on di®erent classi¯cation techniques and the results are evaluated. We also evaluate the performance of this ensemble method against two alternative ensembles. The experimental results demonstrate that our proposed method can improve the performance of the response models for bank direct marketing by raising prediction accuracy and increasing response rate.