The design of tuned mass damper (TMD) parameters is influenced by the soil-structure-TMD coupling system; thus, it is important to consider the soil-structure interaction (SSI) for the vibration control effect of the TMD. Recently, the acquisition of TMD parameters considering soil-structure interactions has only remained at the theoretical stage, lacking relevant experimental verification. Traditional TMD face the problems of occupying a large building space, increasing construction costs, and non-replaceable components. In this study, an assembled wall-type damping TMD was designed. By comparing the dynamic response of the uncontrolled and controlled structures equipped with the newly assembled wall-type damping TMD in the shaking table test on a soft soil foundation, we analyzed whether the SSI effect was considered in the TMD design parameters on the damping effect of the newly assembled wall-type tuned mass damper. The TMD parameters optimized using the artificial intelligence algorithm were verified experimentally. The results indicated that the traditional TMD design parameters were discordant because the SSI effect was not considered. The SSI effect in the soil effectively reduces the dynamic response of the superstructure. By considering the SSI effect and improving the multi-population genetic algorithm, a wall-type damping TMD with optimized parameters can achieve a good damping effect.