The design of experiment for our company will include several steps. First of all, we should define the problem, In the case of our company, it is the low level of e-mail marketing effectiveness. Second, we should define the primary objective that is to increase the response rate to e-mail adverts. Third we should design the experiment determining the factors that will be studied for analysis. The company will use only two of the three factors it has defined: e-mail headings, e-mail open, and e-mail body.
What matters to the company is the customer’s responsiveness. That means that the customer should be interested in, at least, opening the e-mail advertisement. For this reason, there will be two types of interactions determined – e-mail headings (generic or detailed) and e-mail open vs. e-mail body (text or HTML) and e-mail open. Next step is analyzing data and interpreting the results of the experiment. It means that the company will focus on determining whether there is the correlation between the type of e-mail headings and e-mail body and the fact that the customers open the e-mail advertisement, i.e. the measured response (Design of experiments (DOE), n.d.).
I propose using the interaction effect charts for displaying the results of the design of experiment provided above. The reason for this decision is evident – this method is an effective tool for demonstrating what types of e-mail headings and e-mail bodies are more effective when it comes to e-mail marketing. In addition to that, there are two options for preparing the charts. First, there can be one massive chart displaying all factors together. Second, there can be several small charts demonstrating whether there is the correlation between the factors (Peltier, 2010). The choice is in the hands of the company’s management.
The primary objective of our company is to improve the responsiveness to e-mail advertisement. To do so, it should as well make the customers want to open the message before deleting it. There are several strategies that the company might be interested in. I will divide them into two blocks – those that will increase the rate of e-mail open and those that will raise the level of the customer responsiveness. As of the first group of strategies, it is necessary to choose the time of the day when the potential customers do not actively use their e-mail box and are not too busy. The motivation is evident – the client is more likely to pay attention to a message sent, say, in the middle of the night. The reason for it is that he/she will check the e-mail box at the beginning of the day and find just several letters, so the probability of opening it is higher. Second, it is vital to make the e-mail heading catchy and persuade the customer that the content of the letter includes some benefits for him/her (Hafiz, 2014).
When it comes to increasing the rate of responsiveness, the first thing that should be done is providing the customer with the accurate information not overloaded with unnecessary facts (Al-Alwani, 2015). It is always better to include some links to the info that might be useful rather than write it as text. Nobody is interested in reading long advertisements. Finally, it can be beneficial to add sharing and co-registration buttons (Fariborzi, & Zahedifard, 2012). If you provide valuable info, people will likely want to share it with friends. As of co-registration, it is always easier to sign in with the existing profile from, for example, social networks than create a new one.
Lastly, strategy for developing the model for successful business planning should be based on the data defined by the company mentioned above. The most significant step is to try to determine whether some new data and factors should be added. If yes, then the company should conduct the same experiment as proposed once more. If no, it should validate the model and check whether it describes the data well (Spellman, & Whiting, 2014).
References
Al-Alwani, A. (2015). Improving email response in an email management system using natural language processing based probabilistic methods. Journal of Computer Science, 11(1), 109-119.
Design of experiments (DOE). (n.d.)
Fariborzi, E., & Zahedifard, M. (2012). E-mail marketing: Advantages, disadvantages and improving techniques. International Journal of e-Education, e-Business, e-Management and e-Learning, 2(3), 232-236.
Hafiz, M. A. (2014). 12 ways to improve e-mail open and response rates.
Peltier, J. (2010). Main effects and interaction plots.
Spellman, F., & Whiting, N. E. (2014). Handbook of mathematics and statistics for the environment. Boca Raton, FL: Taylor & Francis Group.