Application of Machine Learning in Digital Marketing
M. Vinodhini1, B.Rohith2, T.R.Praveen Kumar3, S.V.L.S.Kranthi Vardhan4
1M.Vinodhini*, Assistant professor of Information Technology in SRM IST Ramapuram, Tamilnadu, India.
2B.Rohith, Department of Information Technology, SRM IST Ramapuram, Tamilnadu, India.
3T.R.Praveen Kumar, Department of Information Technology, SRM IST Ramapuram, Tamilnadu.
4S.V.L.S.Kranthi Vardhan Department of Information Technology, SRMIST ,Ramapuram ,Tamilnadu, India.
Manuscript received on April 08, 2020. | Revised Manuscript received on April 20, 2020. | Manuscript published on May 30, 2020. | PP: 816-818 | Volume-9 Issue-1, May 2020. | Retrieval Number: A1703059120/2020©BEIESP | DOI: 10.35940/ijrte.A1703.059120
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The medication utilization alludes to unforeseen alleviation of sicknesses or side effects when patients take a medication for another known sign. Throughout the entire existence of medication revelation, this has contributed altogether to new and fruitful signs for some medications. Our past research has distinguished patient announced fortunate medication use in internet-based life. On the off chance that such data could be computationally distinguished in internet-based life, it could be useful for producing and approving medication repositioning speculations. The proposed framework outlines recognition of fortunate medication use in online life as a parallel grouping issue and examined profound neural system models as an answer. The proposed framework discovers patients revealed fortunate new signs for the medications they were utilizing for comorbid conditions, which is really significant data for tranquilize repositioning. The proposed framework examines drug results, and solid common language handling and content mining strategies are expected to naturally mine internet-based life information for a huge scope. The proposed framework adds setting data assisted with decreasing the bogus positive pace of profound neural system models. Within the sight of an amazingly imbalanced dataset and constrained cases of fortunate medication utilization, profound neural system models didn’t outflank other AI models with n-gram and setting highlights. Be that as it may, profound neural system models could all the more successfully use word inserting in include development.
Keywords: AI models.
Scope of the Article: Machine Learning